Research connected to "machine learning"

Search papers, authors, topics, institutions and opportunities, then move straight into the graph around the result.

Search results

Showing works 1,729-1,760 from 49,008 works in Machine Learning. Use pages to browse more, or open the graph for the map.

49,008matching works

Shown33 Papers32

Full topic scaleMachine Learning

49,008 works and 109,744 authors are indexed for this topic. This page shows 32 works at a time so search stays fast.

Open topic Open graph

Match modeExact match focus

Semantic hits0

Active filters0

Graph viewOpen

Useful next jumps

Deep Fourier Kernel for Self-Attentive Point Processesworkpreprint / 2021 / arXiv Co-Evolving Policy Distillationworkpreprint / 2026 / arXiv Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learningworkpreprint / 2020 / arXiv Machine Learningtopic49008 works

preprint2021arXiv

Deep Fourier Kernel for Self-Attentive Point Processes

We present a novel attention-based model for discrete event data to capture complex non-linear temporal dependence structures. We borrow the idea from the attention mechanism and incorporate it into the point processes' conditional intensity function. We further introduce a novel score function using Fourier kernel embedding, whose spectrum is represented using neural networks, which drastically differs from the traditional dot-product kernel and can capture a more complex similarity structure. We establish our approach's theoretical properties and demonstrate our approach's competitive performance compared to the state-of-the-art for synthetic and real data.

preprint2026arXiv

Co-Evolving Policy Distillation

RLVR and OPD have become standard paradigms for post-training. We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single model, identifying capability loss in different ways: mixed RLVR suffers from inter-capability divergence cost, while the pipeline of first training experts and then performing OPD, though avoiding divergence, fails to fully absorb teacher capabilities due to large behavioral pattern gaps between teacher and student. We propose Co-Evolving Policy Distillation (CoPD), which encourages parallel training of experts and introduces OPD during each expert's ongoing RLVR training rather than after complete expert training, with experts serving as mutual teachers (making OPD bidirectional) to co-evolve. This enables more consistent behavioral patterns among experts while maintaining sufficient complementary knowledge throughout. Experiments validate that CoPD achieves all-in-one integration of text, image, and video reasoning capabilities, significantly outperforming strong baselines such as mixed RLVR and MOPD, and even surpassing domain-specific experts. The model parallel training pattern offered by CoPD may inspire a novel training scaling paradigm.

preprint2020arXiv

Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning

Option discovery and skill acquisition frameworks are integral to the functioning of a Hierarchically organized Reinforcement learning agent. However, such techniques often yield a large number of options or skills, which can potentially be represented succinctly by filtering out any redundant information. Such a reduction can reduce the required computation while also improving the performance on a target task. In order to compress an array of option policies, we attempt to find a policy basis that accurately captures the set of all options. In this work, we propose Option Encoder, an auto-encoder based framework with intelligently constrained weights, that helps discover a collection of basis policies. The policy basis can be used as a proxy for the original set of skills in a suitable hierarchically organized framework. We demonstrate the efficacy of our method on a collection of grid-worlds and on the high-dimensional Fetch-Reach robotic manipulation task by evaluating the obtained policy basis on a set of downstream tasks.

preprint2023arXiv

Application of machine learning to gas flaring

Currently in the petroleum industry, operators often flare the produced gas instead of commodifying it. The flaring magnitudes are large in some states, which constitute problems with energy waste and CO2 emissions. In North Dakota, operators are required to estimate and report the volume flared. The questions are, how good is the quality of this reporting, and what insights can be drawn from it? Apart from the company-reported statistics, which are available from the North Dakota Industrial Commission (NDIC), flared volumes can be estimated via satellite remote sensing, serving as an unbiased benchmark. Since interpretation of the Landsat 8 imagery is hindered by artifacts due to glow, the estimated volumes based on the Visible Infrared Imaging Radiometer Suite (VIIRS) are used. Reverse geocoding is performed for comparing and contrasting the NDIC and VIIRS data at different levels, such as county and oilfield. With all the data gathered and preprocessed, Bayesian learning implemented by MCMC methods is performed to address three problems: county level model development, flaring time series analytics, and distribution estimation. First, there is heterogeneity among the different counties, in the associations between the NDIC and VIIRS volumes. In light of such, models are developed for each county by exploiting hierarchical models. Second, the flaring time series, albeit noisy, contains information regarding trends and patterns, which provide some insights into operator approaches. Gaussian processes are found to be effective in many different pattern recognition scenarios. Third, distributional insights are obtained through unsupervised learning. The negative binomial and GMMs are found to effectively describe the oilfield flare count and flared volume distributions, respectively. Finally, a nearest-neighbor-based approach for operator level monitoring and analytics is introduced.

preprint2016arXiv

Auxiliary Deep Generative Models

Deep generative models parameterized by neural networks have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave the generative model unchanged but make the variational distribution more expressive. Inspired by the structure of the auxiliary variable we also propose a model with two stochastic layers and skip connections. Our findings suggest that more expressive and properly specified deep generative models converge faster with better results. We show state-of-the-art performance within semi-supervised learning on MNIST, SVHN and NORB datasets.

preprint2022arXiv

Large Scale Transfer Learning for Differentially Private Image Classification

Differential Privacy (DP) provides a formal framework for training machine learning models with individual example level privacy. In the field of deep learning, Differentially Private Stochastic Gradient Descent (DP-SGD) has emerged as a popular private training algorithm. Unfortunately, the computational cost of training large-scale models with DP-SGD is substantially higher than non-private training. This is further exacerbated by the fact that increasing the number of parameters leads to larger degradation in utility with DP. In this work, we zoom in on the ImageNet dataset and demonstrate that, similar to the non-private case, pre-training over-parameterized models on a large public dataset can lead to substantial gains when the model is finetuned privately. Moreover, by systematically comparing private and non-private models across a range of large batch sizes, we find that similar to non-private setting, choice of optimizer can further improve performance substantially with DP. By using LAMB optimizer with DP-SGD we saw improvement of up to 20$\%$ points (absolute). Finally, we show that finetuning just the last layer for a \emph{single step} in the full batch setting, combined with extremely small-scale (near-zero) initialization leads to both SOTA results of 81.7 $\%$ under a wide privacy budget range of $ε\in [4, 10]$ and $δ$ = $10^{-6}$ while minimizing the computational overhead substantially.

preprint2022arXiv

BIMRL: Brain Inspired Meta Reinforcement Learning

Sample efficiency has been a key issue in reinforcement learning (RL). An efficient agent must be able to leverage its prior experiences to quickly adapt to similar, but new tasks and situations. Meta-RL is one attempt at formalizing and addressing this issue. Inspired by recent progress in meta-RL, we introduce BIMRL, a novel multi-layer architecture along with a novel brain-inspired memory module that will help agents quickly adapt to new tasks within a few episodes. We also utilize this memory module to design a novel intrinsic reward that will guide the agent's exploration. Our architecture is inspired by findings in cognitive neuroscience and is compatible with the knowledge on connectivity and functionality of different regions in the brain. We empirically validate the effectiveness of our proposed method by competing with or surpassing the performance of some strong baselines on multiple MiniGrid environments.

preprint2022arXiv

Time-varying Graph Learning Under Structured Temporal Priors

This paper endeavors to learn time-varying graphs by using structured temporal priors that assume underlying relations between arbitrary two graphs in the graph sequence. Different from many existing chain structure based methods in which the priors like temporal homogeneity can only describe the variations of two consecutive graphs, we propose a structure named \emph{temporal graph} to characterize the underlying real temporal relations. Under this framework, the chain structure is actually a special case of our temporal graph. We further proposed Alternating Direction Method of Multipliers (ADMM), a distributed algorithm, to solve the induced optimization problem. Numerical experiments demonstrate the superiorities of our method.

preprint2020arXiv

Federated learning with hierarchical clustering of local updates to improve training on non-IID data

Federated learning (FL) is a well established method for performing machine learning tasks over massively distributed data. However in settings where data is distributed in a non-iid (not independent and identically distributed) fashion -- as is typical in real world situations -- the joint model produced by FL suffers in terms of test set accuracy and/or communication costs compared to training on iid data. We show that learning a single joint model is often not optimal in the presence of certain types of non-iid data. In this work we present a modification to FL by introducing a hierarchical clustering step (FL+HC) to separate clusters of clients by the similarity of their local updates to the global joint model. Once separated, the clusters are trained independently and in parallel on specialised models. We present a robust empirical analysis of the hyperparameters for FL+HC for several iid and non-iid settings. We show how FL+HC allows model training to converge in fewer communication rounds (significantly so under some non-iid settings) compared to FL without clustering. Additionally, FL+HC allows for a greater percentage of clients to reach a target accuracy compared to stand

preprint2022arXiv

Towards Flexible Sparsity-Aware Modeling: Automatic Tensor Rank Learning Using The Generalized Hyperbolic Prior

Tensor rank learning for canonical polyadic decomposition (CPD) has long been deemed as an essential yet challenging problem. In particular, since the tensor rank controls the complexity of the CPD model, its inaccurate learning would cause overfitting to noise or underfitting to the signal sources, and even destroy the interpretability of model parameters. However, the optimal determination of a tensor rank is known to be a non-deterministic polynomial-time hard (NP-hard) task. Rather than exhaustively searching for the best tensor rank via trial-and-error experiments, Bayesian inference under the Gaussian-gamma prior was introduced in the context of probabilistic CPD modeling, and it was shown to be an effective strategy for automatic tensor rank determination. This triggered flourishing research on other structured tensor CPDs with automatic tensor rank learning. On the other side of the coin, these research works also reveal that the Gaussian-gamma model does not perform well for high-rank tensors and/or low signal-to-noise ratios (SNRs). To overcome these drawbacks, in this paper, we introduce a more advanced generalized hyperbolic (GH) prior to the probabilistic CPD model, which not only includes the Gaussian-gamma model as a special case, but also is more flexible to adapt to different levels of sparsity. Based on this novel probabilistic model, an algorithm is developed under the framework of variational inference, where each update is obtained in a closed-form. Extensive numerical results, using synthetic data and real-world datasets, demonstrate the significantly improved performance of the proposed method in learning both low as well as high tensor ranks even for low SNR cases.

preprint2020arXiv

An Effective and Efficient Initialization Scheme for Training Multi-layer Feedforward Neural Networks

Network initialization is the first and critical step for training neural networks. In this paper, we propose a novel network initialization scheme based on the celebrated Stein's identity. By viewing multi-layer feedforward neural networks as cascades of multi-index models, the projection weights to the first hidden layer are initialized using eigenvectors of the cross-moment matrix between the input's second-order score function and the response. The input data is then forward propagated to the next layer and such a procedure can be repeated until all the hidden layers are initialized. Finally, the weights for the output layer are initialized by generalized linear modeling. Such a proposed SteinGLM method is shown through extensive numerical results to be much faster and more accurate than other popular methods commonly used for training neural networks.

preprint2022arXiv

Online Coreset Selection for Rehearsal-based Continual Learning

A dataset is a shred of crucial evidence to describe a task. However, each data point in the dataset does not have the same potential, as some of the data points can be more representative or informative than others. This unequal importance among the data points may have a large impact in rehearsal-based continual learning, where we store a subset of the training examples (coreset) to be replayed later to alleviate catastrophic forgetting. In continual learning, the quality of the samples stored in the coreset directly affects the model's effectiveness and efficiency. The coreset selection problem becomes even more important under realistic settings, such as imbalanced continual learning or noisy data scenarios. To tackle this problem, we propose Online Coreset Selection (OCS), a simple yet effective method that selects the most representative and informative coreset at each iteration and trains them in an online manner. Our proposed method maximizes the model's adaptation to a current dataset while selecting high-affinity samples to past tasks, which directly inhibits catastrophic forgetting. We validate the effectiveness of our coreset selection mechanism over various standard, imbalanced, and noisy datasets against strong continual learning baselines, demonstrating that it improves task adaptation and prevents catastrophic forgetting in a sample-efficient manner.

preprint2022arXiv

Enhancing Adversarial Attacks on Single-Layer NVM Crossbar-Based Neural Networks with Power Consumption Information

Adversarial attacks on state-of-the-art machine learning models pose a significant threat to the safety and security of mission-critical autonomous systems. This paper considers the additional vulnerability of machine learning models when attackers can measure the power consumption of their underlying hardware platform. In particular, we explore the utility of power consumption information for adversarial attacks on non-volatile memory crossbar-based single-layer neural networks. Our results from experiments with MNIST and CIFAR-10 datasets show that power consumption can reveal important information about the neural network's weight matrix, such as the 1-norm of its columns. That information can be used to infer the sensitivity of the network's loss with respect to different inputs. We also find that surrogate-based black box attacks that utilize crossbar power information can lead to improved attack efficiency.

preprint2021arXiv

HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving

Humans learn compositional and causal abstraction, \ie, knowledge, in response to the structure of naturalistic tasks. When presented with a problem-solving task involving some objects, toddlers would first interact with these objects to reckon what they are and what can be done with them. Leveraging these concepts, they could understand the internal structure of this task, without seeing all of the problem instances. Remarkably, they further build cognitively executable strategies to \emph{rapidly} solve novel problems. To empower a learning agent with similar capability, we argue there shall be three levels of generalization in how an agent represents its knowledge: perceptual, conceptual, and algorithmic. In this paper, we devise the very first systematic benchmark that offers joint evaluation covering all three levels. This benchmark is centered around a novel task domain, HALMA, for visual concept development and rapid problem-solving. Uniquely, HALMA has a minimum yet complete concept space, upon which we introduce a novel paradigm to rigorously diagnose and dissect learning agents' capability in understanding and generalizing complex and structural concepts. We conduct extensive experiments on reinforcement learning agents with various inductive biases and carefully report their proficiency and weakness.

preprint2020arXiv

An Uncoupled Training Architecture for Large Graph Learning

Graph Convolutional Network (GCN) has been widely used in graph learning tasks. However, GCN-based models (GCNs) is an inherently coupled training framework repetitively conducting the complex neighboring aggregation, which leads to the limitation of flexibility in processing large-scale graph. With the depth of layers increases, the computational and memory cost of GCNs grow explosively due to the recursive neighborhood expansion. To tackle these issues, we present Node2Grids, a flexible uncoupled training framework that leverages the independent mapped data for obtaining the embedding. Instead of directly processing the coupled nodes as GCNs, Node2Grids supports a more efficacious method in practice, mapping the coupled graph data into the independent grid-like data which can be fed into the efficient Convolutional Neural Network (CNN). This simple but valid strategy significantly saves memory and computational resource while achieving comparable results with the leading GCN-based models. Specifically, by ranking each node's influence through degree, Node2Grids selects the most influential first-order as well as second-order neighbors with central node fusion information to c

preprint2022arXiv

The Multi-Agent Pickup and Delivery Problem: MAPF, MARL and Its Warehouse Applications

We study two state-of-the-art solutions to the multi-agent pickup and delivery (MAPD) problem based on different principles -- multi-agent path-finding (MAPF) and multi-agent reinforcement learning (MARL). Specifically, a recent MAPF algorithm called conflict-based search (CBS) and a current MARL algorithm called shared experience actor-critic (SEAC) are studied. While the performance of these algorithms is measured using quite different metrics in their separate lines of work, we aim to benchmark these two methods comprehensively in a simulated warehouse automation environment.

preprint2022arXiv

Learning (Very) Simple Generative Models Is Hard

Motivated by the recent empirical successes of deep generative models, we study the computational complexity of the following unsupervised learning problem. For an unknown neural network $F:\mathbb{R}^d\to\mathbb{R}^{d'}$, let $D$ be the distribution over $\mathbb{R}^{d'}$ given by pushing the standard Gaussian $\mathcal{N}(0,\textrm{Id}_d)$ through $F$. Given i.i.d. samples from $D$, the goal is to output any distribution close to $D$ in statistical distance. We show under the statistical query (SQ) model that no polynomial-time algorithm can solve this problem even when the output coordinates of $F$ are one-hidden-layer ReLU networks with $\log(d)$ neurons. Previously, the best lower bounds for this problem simply followed from lower bounds for supervised learning and required at least two hidden layers and $\mathrm{poly}(d)$ neurons [Daniely-Vardi '21, Chen-Gollakota-Klivans-Meka '22]. The key ingredient in our proof is an ODE-based construction of a compactly supported, piecewise-linear function $f$ with polynomially-bounded slopes such that the pushforward of $\mathcal{N}(0,1)$ under $f$ matches all low-degree moments of $\mathcal{N}(0,1)$.

preprint2020arXiv

DALC: Distributed Automatic LSTM Customization for Fine-Grained Traffic Speed Prediction

Over the past decade, several approaches have been introduced for short-term traffic prediction. However, providing fine-grained traffic prediction for large-scale transportation networks where numerous detectors are geographically deployed to collect traffic data is still an open issue. To address this issue, in this paper, we formulate the problem of customizing an LSTM model for a single detector into a finite Markov decision process and then introduce an Automatic LSTM Customization (ALC) algorithm to automatically customize an LSTM model for a single detector such that the corresponding prediction accuracy can be as satisfactory as possible and the time consumption can be as low as possible. Based on the ALC algorithm, we introduce a distributed approach called Distributed Automatic LSTM Customization (DALC) to customize an LSTM model for every detector in large-scale transportation networks. Our experiment demonstrates that the DALC provides higher prediction accuracy than several approaches provided by Apache Spark MLlib.

preprint2026arXiv

RelAgent: LLM Agents as Data Scientists for Relational Learning

Relational learning is a challenging problem that has motivated a wide range of approaches, including graph-based models (e.g., graph neural networks, graph transformers), tabular methods (e.g., tabular foundation models), and sequence-based approaches (e.g., large language models), each with its own advantages and limitations. We propose RelAgent, an LLM-based autonomous data scientist for relational learning, which operates in two phases. In the search phase, an LLM agent uses database, validation, and evaluation workspace tools to construct SQL feature programs and select a predictive model. In the inference phase, the resulting program is executed without further LLM calls. The final predictor consists of SQL queries and a classical model, enabling fast, deterministic, and intrinsically interpretable predictions: features are human-readable queries, and predictions depend only on the resulting query-defined feature map, enabling scalable deployment using standard database systems.

preprint2014arXiv

Score Function Features for Discriminative Learning: Matrix and Tensor Framework

Feature learning forms the cornerstone for tackling challenging learning problems in domains such as speech, computer vision and natural language processing. In this paper, we consider a novel class of matrix and tensor-valued features, which can be pre-trained using unlabeled samples. We present efficient algorithms for extracting discriminative information, given these pre-trained features and labeled samples for any related task. Our class of features are based on higher-order score functions, which capture local variations in the probability density function of the input. We establish a theoretical framework to characterize the nature of discriminative information that can be extracted from score-function features, when used in conjunction with labeled samples. We employ efficient spectral decomposition algorithms (on matrices and tensors) for extracting discriminative components. The advantage of employing tensor-valued features is that we can extract richer discriminative information in the form of an overcomplete representations. Thus, we present a novel framework for employing generative models of the input for discriminative learning.

preprint2026arXiv

Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate

Compile-pass rate is the dominant evaluation signal for LLM code generation, yet for multi-component domain-specific artifacts it can be actively misleading. We demonstrate this on executable game scene synthesis with a four-axis evaluation protocol (named `Mage') -- compile success, runtime success, structural fidelity, and mechanism adherence -- applied to 858 generation attempts across four open-weight LLMs (7B--30B), 26~hand-crafted Unity goal pattern playable concepts, and two automatically extracted IR granularity levels. Direct NL-to-C\# generation achieves the highest runtime-pass rate (43\% mean) yet produces structurally vacuous scenes (mechanism $F_1 \approx 0.12$). Structural IR conditioning halves the runtime rate but recovers domain-faithful structure ($F_1$ up to 1.00). Within IR conditioning, behavior-only and full-scene granularity are statistically indistinguishable (McNemar $p = 1.0$), indicating input-level granularity saturation. These results show that compile rate is anti-correlated with functional correctness in this domain and that multi-axis evaluation is necessary to detect the divergence. We release the benchmark, replay logs, and per-record metrics for independent verification.

preprint2016arXiv

Multi-task and Lifelong Learning of Kernels

We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneously is beneficial over single task learning. In particular, as the number of observed tasks grows, assuming that in the considered family of kernels there exists one that yields low approximation error on all tasks, the overhead associated with learning such a kernel vanishes and the complexity converges to that of learning when this good kernel is given to the learner.

preprint2012arXiv

A Method of Moments for Mixture Models and Hidden Markov Models

Mixture models are a fundamental tool in applied statistics and machine learning for treating data taken from multiple subpopulations. The current practice for estimating the parameters of such models relies on local search heuristics (e.g., the EM algorithm) which are prone to failure, and existing consistent methods are unfavorable due to their high computational and sample complexity which typically scale exponentially with the number of mixture components. This work develops an efficient method of moments approach to parameter estimation for a broad class of high-dimensional mixture models with many components, including multi-view mixtures of Gaussians (such as mixtures of axis-aligned Gaussians) and hidden Markov models. The new method leads to rigorous unsupervised learning results for mixture models that were not achieved by previous works; and, because of its simplicity, it offers a viable alternative to EM for practical deployment.

preprint2022arXiv

Adaptive Clustering and Personalization in Multi-Agent Stochastic Linear Bandits

We consider the problem of minimizing regret in an $N$ agent heterogeneous stochastic linear bandits framework, where the agents (users) are similar but not all identical. We model user heterogeneity using two popularly used ideas in practice; (i) A clustering framework where users are partitioned into groups with users in the same group being identical to each other, but different across groups, and (ii) a personalization framework where no two users are necessarily identical, but a user's parameters are close to that of the population average. In the clustered users' setup, we propose a novel algorithm, based on successive refinement of cluster identities and regret minimization. We show that, for any agent, the regret scales as $\mathcal{O}(\sqrt{T/N})$, if the agent is in a `well separated' cluster, or scales as $\mathcal{O}(T^{\frac{1}{2} + \varepsilon}/(N)^{\frac{1}{2} -\varepsilon})$ if its cluster is not well separated, where $\varepsilon$ is positive and arbitrarily close to $0$. Our algorithm is adaptive to the cluster separation, and is parameter free -- it does not need to know the number of clusters, separation and cluster size, yet the regret guarantee adapts to the inherent complexity. In the personalization framework, we introduce a natural algorithm where, the personal bandit instances are initialized with the estimates of the global average model. We show that, an agent $i$ whose parameter deviates from the population average by $ε_i$, attains a regret scaling of $\widetilde{O}(ε_i\sqrt{T})$. This demonstrates that if the user representations are close (small $ε_i)$, the resulting regret is low, and vice-versa. The results are empirically validated and we observe superior performance of our adaptive algorithms over non-adaptive baselines.

preprint2013arXiv

Validation of Soft Classification Models using Partial Class Memberships: An Extended Concept of Sensitivity & Co. applied to the Grading of Astrocytoma Tissues

We use partial class memberships in soft classification to model uncertain labelling and mixtures of classes. Partial class memberships are not restricted to predictions, but may also occur in reference labels (ground truth, gold standard diagnosis) for training and validation data. Classifier performance is usually expressed as fractions of the confusion matrix, such as sensitivity, specificity, negative and positive predictive values. We extend this concept to soft classification and discuss the bias and variance properties of the extended performance measures. Ambiguity in reference labels translates to differences between best-case, expected and worst-case performance. We show a second set of measures comparing expected and ideal performance which is closely related to regression performance, namely the root mean squared error RMSE and the mean absolute error MAE. All calculations apply to classical crisp classification as well as to soft classification (partial class memberships and/or one-class classifiers). The proposed performance measures allow to test classifiers with actual borderline cases. In addition, hardening of e.g. posterior probabilities into class labels is not

preprint2022arXiv

Inter- and Intra-Series Embeddings Fusion Network for Epidemiological Forecasting

The accurate forecasting of infectious epidemic diseases is the key to effective control of the epidemic situation in a region. Most existing methods ignore potential dynamic dependencies between regions or the importance of temporal dependencies and inter-dependencies between regions for prediction. In this paper, we propose an Inter- and Intra-Series Embeddings Fusion Network (SEFNet) to improve epidemic prediction performance. SEFNet consists of two parallel modules, named Inter-Series Embedding Module and Intra-Series Embedding Module. In Inter-Series Embedding Module, a multi-scale unified convolution component called Region-Aware Convolution is proposed, which cooperates with self-attention to capture dynamic dependencies between time series obtained from multiple regions. The Intra-Series Embedding Module uses Long Short-Term Memory to capture temporal relationships within each time series. Subsequently, we learn the influence degree of two embeddings and fuse them with the parametric-matrix fusion method. To further improve the robustness, SEFNet also integrates a traditional autoregressive component in parallel with nonlinear neural networks. Experiments on four real-world epidemic-related datasets show SEFNet is effective and outperforms state-of-the-art baselines.

preprint2026arXiv

Learning to Forget: Continual Learning with Adaptive Weight Decay

Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowledge that is no longer needed, freeing up capacity to learn. Weight decay, viewed as a mechanism for forgetting, can serve this role by gradually discarding information stored in the weights. However, a fixed scalar weight decay drives this forgetting uniformly over time and uniformly across all parameters, even when some encode stable knowledge while others track rapidly changing targets. We introduce Forgetting through Adaptive Decay (FADE), which adapts per-parameter weight decay rates online via approximate meta-gradient descent. We derive FADE for the online linear setting and apply it to the final layer of neural networks. Our empirical analysis shows that FADE automatically discovers distinct decay rates for different parameters, complements step-size adaptation, and consistently improves over fixed weight decay across online tracking and streaming classification problems.

preprint2026arXiv

Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification

Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical reasoning or hidden-test execution in code generation. We formalize this setting using a learning-theoretic lens as generative active search: a cost-sensitive first-positive search problem in which a policy adaptively samples candidates from an unknown distribution, observes cheap scores, and pays for verifier labels until it finds a positive example. For a fixed prompt, the generator and reward model induce two unknown objects: a distribution over reward scores and a score-conditioned success function. When these quantities are known, we characterize the distribution-aware optimal policy using a dynamic programming approach. In the realistic and practical setting where both the score distribution and success function are unknown, we propose ADAP, a shellwise adaptive generate-rank-verify algorithm that progressively increases the number of sampled responses and top-ranked verifications. Under the monotonicity assumption that higher reward scores are no less likely to pass verification, we show that ADAP achieves expected cost within a constant factor of the distribution-aware optimum. We complement this result with learning-theoretic lower bounds, based on a centered star number, showing that structural assumptions on the score--label relationship are necessary. Experiments on mathematical reasoning and competitive programming validate the predicted advantage over both fixed non-adaptive policies and difficulty-adaptive baselines.

preprint2026arXiv

What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition

Graph neural networks are widely used for node classification, but they remain vulnerable to out-of-distribution (OOD) shifts in node features and graph structure. Prior work established that methods trained with standard supervised learning (SL) objectives tend to capture spurious signals from either features and/or structure, leaving the model fragile under distributional changes. To address this, we propose TIDE, a novel and effective Tri-Component Information Decomposition framework that explicitly decomposes information into feature-specific, structure-specific and joint components. TIDE aims to preserve only the label-relevant part of the joint information while filtering out spurious feature- and structure-specific information, thereby enhancing the separation between in-distribution (ID) and OOD nodes. Beyond the framework, we provide theoretical and empirical analyses showing that an information bottleneck objective is preferable to standard SL for graph OOD detection, with higher ID confidence and a greater entropy gap between ID and OOD data. Extensive experiments across seven datasets confirm the efficacy of TIDE, achieving up to a 34% improvement in FPR95 over strong baselines while maintaining competitive ID accuracy.

preprint2026arXiv

Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix

Transformer-based architectures have become the dominant paradigm for Continuous-Time Dynamic Graph (CTDG) learning, yet their performance remains limited on temporally shifted datasets. In this work, we identify attention dispersion as a shared failure mode of dynamic graph Transformers under temporal distribution shift. Through controlled ablation contrasting structurally and temporally distinguished historical neighbors against random ones, we show that prediction depends on a class of critical nodes that carry consistently more predictive signal than arbitrary neighbors. However, existing Transformers fail to focus on these nodes even when they are present in the input, as temporal shift weakens attention contrast and produces overly dispersed attention distributions. This diagnosis suggests a simple and transferable fix: replace standard attention with differential attention, which suppresses common-mode attention and amplifies distinctive token-level signals. When added to three representative CTDG Transformer baselines, differential attention consistently improves performance, with gains concentrated on high-shift datasets. Attention-level measurements further confirm the mechanism, showing reduced attention entropy and increased attention mass on critical nodes. Building on these findings, we introduce DiffDyG, a reference implementation combining differential attention with standard input encodings. Across 9 benchmarks and three negative sampling protocols, DiffDyG achieves SOTA performance, with especially large gains on the most shifted datasets.

preprint2018arXiv

Offline EEG-Based Driver Drowsiness Estimation Using Enhanced Batch-Mode Active Learning (EBMAL) for Regression

There are many important regression problems in real-world brain-computer interface (BCI) applications, e.g., driver drowsiness estimation from EEG signals. This paper considers offline analysis: given a pool of unlabeled EEG epochs recorded during driving, how do we optimally select a small number of them to label so that an accurate regression model can be built from them to label the rest? Active learning is a promising solution to this problem, but interestingly, to our best knowledge, it has not been used for regression problems in BCI so far. This paper proposes a novel enhanced batch-mode active learning (EBMAL) approach for regression, which improves upon a baseline active learning algorithm by increasing the reliability, representativeness and diversity of the selected samples to achieve better regression performance. We validate its effectiveness using driver drowsiness estimation from EEG signals. However, EBMAL is a general approach that can also be applied to many other offline regression problems beyond BCI.

preprint2022arXiv

Learning Deep Implicit Fourier Neural Operators (IFNOs) with Applications to Heterogeneous Material Modeling

Constitutive modeling based on continuum mechanics theory has been a classical approach for modeling the mechanical responses of materials. However, when constitutive laws are unknown or when defects and/or high degrees of heterogeneity are present, these classical models may become inaccurate. In this work, we propose to use data-driven modeling, which directly utilizes high-fidelity simulation and/or experimental measurements to predict a material's response without using conventional constitutive models. Specifically, the material response is modeled by learning the implicit mappings between loading conditions and the resultant displacement and/or damage fields, with the neural network serving as a surrogate for a solution operator. To model the complex responses due to material heterogeneity and defects, we develop a novel deep neural operator architecture, which we coin as the Implicit Fourier Neural Operator (IFNO). In the IFNO, the increment between layers is modeled as an integral operator to capture the long-range dependencies in the feature space. As the network gets deeper, the limit of IFNO becomes a fixed point equation that yields an implicit neural operator and naturally mimics the displacement/damage fields solving procedure in material modeling problems. We demonstrate the performance of our proposed method for a number of examples, including hyperelastic, anisotropic and brittle materials. As an application, we further employ the proposed approach to learn the material models directly from digital image correlation (DIC) tracking measurements, and show that the learned solution operators substantially outperform the conventional constitutive models in predicting displacement fields.