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 1,921-1,952 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

Pre-insertion resistors temperature prediction based on improved WOA-SVRworkpreprint / 2024 / arXiv HopGAT: Hop-aware Supervision Graph Attention Networks for Sparsely Labeled Graphsworkpreprint / 2020 / arXiv Discriminative Feature Learning Framework with Gradient Preference for Anomaly Detectionworkpreprint / 2022 / arXiv Machine Learningtopic49008 works

preprint2024arXiv

Pre-insertion resistors temperature prediction based on improved WOA-SVR

The pre-insertion resistors (PIR) within high-voltage circuit breakers are critical components and warm up by generating Joule heat when an electric current flows through them. Elevated temperature can lead to temporary closure failure and, in severe cases, the rupture of PIR. To accurately predict the temperature of PIR, this study combines finite element simulation techniques with Support Vector Regression (SVR) optimized by an Improved Whale Optimization Algorithm (IWOA) approach. The IWOA includes Tent mapping, a convergence factor based on the sigmoid function, and the Ornstein-Uhlenbeck variation strategy. The IWOA-SVR model is compared with the SSA-SVR and WOA-SVR. The results reveal that the prediction accuracies of the IWOA-SVR model were 90.2% and 81.5% (above 100$^\circ$C) in the 3$^\circ$C temperature deviation range and 96.3% and 93.4% (above 100$^\circ$C) in the 4$^\circ$C temperature deviation range, surpassing the performance of the comparative models. This research demonstrates the method proposed can realize the online monitoring of the temperature of the PIR, which can effectively prevent thermal faults PIR and provide a basis for the opening and closing of the circuit breaker within a short period.

preprint2020arXiv

HopGAT: Hop-aware Supervision Graph Attention Networks for Sparsely Labeled Graphs

Due to the cost of labeling nodes, classifying a node in a sparsely labeled graph while maintaining the prediction accuracy deserves attention. The key point is how the algorithm learns sufficient information from more neighbors with different hop distances. This study first proposes a hop-aware attention supervision mechanism for the node classification task. A simulated annealing learning strategy is then adopted to balance two learning tasks, node classification and the hop-aware attention coefficients, along the training timeline. Compared with state-of-the-art models, the experimental results proved the superior effectiveness of the proposed Hop-aware Supervision Graph Attention Networks (HopGAT) model. Especially, for the protein-protein interaction network, in a 40% labeled graph, the performance loss is only 3.9%, from 98.5% to 94.6%, compared to the fully labeled graph. Extensive experiments also demonstrate the effectiveness of supervised attention coefficient and learning strategies.

preprint2022arXiv

Discriminative Feature Learning Framework with Gradient Preference for Anomaly Detection

Unsupervised representation learning has been extensively employed in anomaly detection, achieving impressive performance. Extracting valuable feature vectors that can remarkably improve the performance of anomaly detection are essential in unsupervised representation learning. To this end, we propose a novel discriminative feature learning framework with gradient preference for anomaly detection. Specifically, we firstly design a gradient preference based selector to store powerful feature points in space and then construct a feature repository, which alleviate the interference of redundant feature vectors and improve inference efficiency. To overcome the looseness of feature vectors, secondly, we present a discriminative feature learning with center constrain to map the feature repository to a compact subspace, so that the anomalous samples are more distinguishable from the normal ones. Moreover, our method can be easily extended to anomaly localization. Extensive experiments on popular industrial and medical anomaly detection datasets demonstrate our proposed framework can achieve competitive results in both anomaly detection and localization. More important, our method outperforms the state-of-the-art in few shot anomaly detection.

preprint2023arXiv

A Classification of $G$-invariant Shallow Neural Networks

When trying to fit a deep neural network (DNN) to a $G$-invariant target function with $G$ a group, it only makes sense to constrain the DNN to be $G$-invariant as well. However, there can be many different ways to do this, thus raising the problem of ``$G$-invariant neural architecture design'': What is the optimal $G$-invariant architecture for a given problem? Before we can consider the optimization problem itself, we must understand the search space, the architectures in it, and how they relate to one another. In this paper, we take a first step towards this goal; we prove a theorem that gives a classification of all $G$-invariant single-hidden-layer or ``shallow'' neural network ($G$-SNN) architectures with ReLU activation for any finite orthogonal group $G$, and we prove a second theorem that characterizes the inclusion maps or ``network morphisms'' between the architectures that can be leveraged during neural architecture search (NAS). The proof is based on a correspondence of every $G$-SNN to a signed permutation representation of $G$ acting on the hidden neurons; the classification is equivalently given in terms of the first cohomology classes of $G$, thus admitting a topological interpretation. The $G$-SNN architectures corresponding to nontrivial cohomology classes have, to our knowledge, never been explicitly identified in the literature previously. Using a code implementation, we enumerate the $G$-SNN architectures for some example groups $G$ and visualize their structure. Finally, we prove that architectures corresponding to inequivalent cohomology classes coincide in function space only when their weight matrices are zero, and we discuss the implications of this for NAS.

preprint2020arXiv

Neural Networks for Relational Data

While deep networks have been enormously successful over the last decade, they rely on flat-feature vector representations, which makes them unsuitable for richly structured domains such as those arising in applications like social network analysis. Such domains rely on relational representations to capture complex relationships between entities and their attributes. Thus, we consider the problem of learning neural networks for relational data. We distinguish ourselves from current approaches that rely on expert hand-coded rules by learning relational random-walk-based features to capture local structural interactions and the resulting network architecture. We further exploit parameter tying of the network weights of the resulting relational neural network, where instances of the same type share parameters. Our experimental results across several standard relational data sets demonstrate the effectiveness of the proposed approach over multiple neural net baselines as well as state-of-the-art statistical relational models.

preprint2020arXiv

Intermittent Inference with Nonuniformly Compressed Multi-Exit Neural Network for Energy Harvesting Powered Devices

This work aims to enable persistent, event-driven sensing and decision capabilities for energy-harvesting (EH)-powered devices by deploying lightweight DNNs onto EH-powered devices. However, harvested energy is usually weak and unpredictable and even lightweight DNNs take multiple power cycles to finish one inference. To eliminate the indefinite long wait to accumulate energy for one inference and to optimize the accuracy, we developed a power trace-aware and exit-guided network compression algorithm to compress and deploy multi-exit neural networks to EH-powered microcontrollers (MCUs) and select exits during execution according to available energy. The experimental results show superior accuracy and latency compared with state-of-the-art techniques.

preprint2021arXiv

Dynamic Embeddings for Interaction Prediction

In recommender systems (RSs), predicting the next item that a user interacts with is critical for user retention. While the last decade has seen an explosion of RSs aimed at identifying relevant items that match user preferences, there is still a range of aspects that could be considered to further improve their performance. For example, often RSs are centered around the user, who is modeled using her recent sequence of activities. Recent studies, however, have shown the effectiveness of modeling the mutual interactions between users and items using separate user and item embeddings. Building on the success of these studies, we propose a novel method called DeePRed that addresses some of their limitations. In particular, we avoid recursive and costly interactions between consecutive short-term embeddings by using long-term (stationary) embeddings as a proxy. This enable us to train DeePRed using simple mini-batches without the overhead of specialized mini-batches proposed in previous studies. Moreover, DeePRed's effectiveness comes from the aforementioned design and a multi-way attention mechanism that inspects user-item compatibility. Experiments show that DeePRed outperforms the best state-of-the-art approach by at least 14% on next item prediction task, while gaining more than an order of magnitude speedup over the best performing baselines. Although this study is mainly concerned with temporal interaction networks, we also show the power and flexibility of DeePRed by adapting it to the case of static interaction networks, substituting the short- and long-term aspects with local and global ones.

preprint2016arXiv

Predicting Counterfactuals from Large Historical Data and Small Randomized Trials

When a new treatment is considered for use, whether a pharmaceutical drug or a search engine ranking algorithm, a typical question that arises is, will its performance exceed that of the current treatment? The conventional way to answer this counterfactual question is to estimate the effect of the new treatment in comparison to that of the conventional treatment by running a controlled, randomized experiment. While this approach theoretically ensures an unbiased estimator, it suffers from several drawbacks, including the difficulty in finding representative experimental populations as well as the cost of running such trials. Moreover, such trials neglect the huge quantities of available control-condition data which are often completely ignored. In this paper we propose a discriminative framework for estimating the performance of a new treatment given a large dataset of the control condition and data from a small (and possibly unrepresentative) randomized trial comparing new and old treatments. Our objective, which requires minimal assumptions on the treatments, models the relation between the outcomes of the different conditions. This allows us to not only estimate mean effects but

preprint2022arXiv

Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes

Deep neural networks (DNNs) are notorious for making more mistakes for the classes that have substantially fewer samples than the others during training. Such class imbalance is ubiquitous in clinical applications and very crucial to handle because the classes with fewer samples most often correspond to critical cases (e.g., cancer) where misclassifications can have severe consequences. Not to miss such cases, binary classifiers need to be operated at high True Positive Rates (TPRs) by setting a higher threshold, but this comes at the cost of very high False Positive Rates (FPRs) for problems with class imbalance. Existing methods for learning under class imbalance most often do not take this into account. We argue that prediction accuracy should be improved by emphasizing reducing FPRs at high TPRs for problems where misclassification of the positive, i.e. critical, class samples are associated with higher cost. To this end, we pose the training of a DNN for binary classification as a constrained optimization problem and introduce a novel constraint that can be used with existing loss functions to enforce maximal area under the ROC curve (AUC) through prioritizing FPR reduction at high TPR. We solve the resulting constrained optimization problem using an Augmented Lagrangian method (ALM). Going beyond binary, we also propose two possible extensions of the proposed constraint for multi-class classification problems. We present experimental results for image-based binary and multi-class classification applications using an in-house medical imaging dataset, CIFAR10, and CIFAR100. Our results demonstrate that the proposed method improves the baselines in majority of the cases by attaining higher accuracy on critical classes while reducing the misclassification rate for the non-critical class samples.

preprint2024arXiv

Efficient selective attention LSTM for well log curve synthesis

Non-core drilling has gradually become the primary exploration method in geological exploration engineering, and well logging curves have increasingly gained importance as the main carriers of geological information. However, factors such as geological environment, logging equipment, borehole quality, and unexpected events can all impact the quality of well logging curves. Previous methods of re-logging or manual corrections have been associated with high costs and low efficiency. This paper proposes a machine learning method that utilizes existing data to predict missing data, and its effectiveness and feasibility have been validated through field experiments. The proposed method builds on the traditional Long Short-Term Memory (LSTM) neural network by incorporating a self-attention mechanism to analyze the sequential dependencies of the data. It selects the dominant computational results in the LSTM, reducing the computational complexity from O(n^2) to O(nlogn) and improving model efficiency. Experimental results demonstrate that the proposed method achieves higher accuracy compared to traditional curve synthesis methods based on Fully Connected Neural Networks (FCNN) and vanilla LSTM. This accurate, efficient, and cost-effective prediction method holds a practical value in engineering applications.

preprint2026arXiv

GRAFT: Graph-Tokenized LLMs for Tool Planning

Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps. This requires aligning tool choices with subtask intent while satisfying directional execution dependencies among tools. To do this, existing methods model these dependencies as tool graphs and incorporate the graphs with LLMs through retrieval, serialization, or prompt-level injection. However, these external graph-use strategies all follow a matching paradigm, which often fails to align tool choices with the underlying subtask structure, producing semantically plausible plans that violate graph constraints. This issue is further exacerbated by error accumulation, where an early incorrect tool selection shifts the plan into an invalid graph state and causes subsequent predictions to drift away from the valid execution path. To address these challenges, we propose GRAFT, a graph-tokenized language model framework for dependency-aware tool planning. GRAFT internalizes the tool graph by mapping each tool node to a dedicated special token and learning directed tool dependencies within the representation space. It further introduces on-policy tool context distillation, training the model on its own sampled trajectories while distilling stepwise planning signals. Experiments show that GRAFT achieves state-of-the-art performance in exact sequence matching and dependency legality, supporting more reliable LLM tool planning in complex workflows.

preprint2022arXiv

Oblique and rotation double random forest

Random Forest is an ensemble of decision trees based on the bagging and random subspace concepts. As suggested by Breiman, the strength of unstable learners and the diversity among them are the ensemble models' core strength. In this paper, we propose two approaches known as oblique and rotation double random forests. In the first approach, we propose rotation based double random forest. In rotation based double random forests, transformation or rotation of the feature space is generated at each node. At each node different random feature subspace is chosen for evaluation, hence the transformation at each node is different. Different transformations result in better diversity among the base learners and hence, better generalization performance. With the double random forest as base learner, the data at each node is transformed via two different transformations namely, principal component analysis and linear discriminant analysis. In the second approach, we propose oblique double random forest. Decision trees in random forest and double random forest are univariate, and this results in the generation of axis parallel split which fails to capture the geometric structure of the data. Also, the standard random forest may not grow sufficiently large decision trees resulting in suboptimal performance. To capture the geometric properties and to grow the decision trees of sufficient depth, we propose oblique double random forest. The oblique double random forest models are multivariate decision trees. At each non-leaf node, multisurface proximal support vector machine generates the optimal plane for better generalization performance. Also, different regularization techniques are employed for tackling the small sample size problems in the decision trees of oblique double random forest.

preprint2022arXiv

Causal Influences Decouple From Their Underlying Network Structure In Echo State Networks

Echo State Networks (ESN) are versatile recurrent neural network models in which the hidden layer remains unaltered during training. Interactions among nodes of this static backbone produce diverse representations of the given stimuli that are harnessed by a read-out mechanism to perform computations needed for solving a given task. ESNs are accessible models of neuronal circuits, since they are relatively inexpensive to train. Therefore, ESNs have become attractive for neuroscientists studying the relationship between neural structure, function, and behavior. For instance, it is not yet clear how distinctive connectivity patterns of brain networks support effective interactions among their nodes and how these patterns of interactions give rise to computation. To address this question, we employed an ESN with a biologically inspired structure and used a systematic multi-site lesioning framework to quantify the causal contribution of each node to the network's output, thus providing a causal link between network structure and behavior. We then focused on the structure-function relationship and decomposed the causal influence of each node on all other nodes, using the same lesioning framework. We found that nodes in a properly engineered ESN interact largely irrespective of the network's underlying structure. However, in a network with the same topology and a non-optimal parameter set, the underlying connectivity patterns determine the node interactions. Our results suggest that causal structure-function relations in ESNs can be decomposed into two components, direct and indirect interactions. The former are based on influences relying on structural connections. The latter describe the effective communication between any two nodes through other intermediate nodes. These widely distributed indirect interactions may crucially contribute to the efficient performance of ESNs.

preprint2013arXiv

Boltzmann Machines and Denoising Autoencoders for Image Denoising

Image denoising based on a probabilistic model of local image patches has been employed by various researchers, and recently a deep (denoising) autoencoder has been proposed by Burger et al. [2012] and Xie et al. [2012] as a good model for this. In this paper, we propose that another popular family of models in the field of deep learning, called Boltzmann machines, can perform image denoising as well as, or in certain cases of high level of noise, better than denoising autoencoders. We empirically evaluate the two models on three different sets of images with different types and levels of noise. Throughout the experiments we also examine the effect of the depth of the models. The experiments confirmed our claim and revealed that the performance can be improved by adding more hidden layers, especially when the level of noise is high.

preprint2019arXiv

Introducing Super Pseudo Panels: Application to Transport Preference Dynamics

We propose a new approach for constructing synthetic pseudo-panel data from cross-sectional data. The pseudo panel and the preferences it intends to describe is constructed at the individual level and is not affected by aggregation bias across cohorts. This is accomplished by creating a high-dimensional probabilistic model representation of the entire data set, which allows sampling from the probabilistic model in such a way that all of the intrinsic correlation properties of the original data are preserved. The key to this is the use of deep learning algorithms based on the Conditional Variational Autoencoder (CVAE) framework. From a modelling perspective, the concept of a model-based resampling creates a number of opportunities in that data can be organized and constructed to serve very specific needs of which the forming of heterogeneous pseudo panels represents one. The advantage, in that respect, is the ability to trade a serious aggregation bias (when aggregating into cohorts) for an unsystematic noise disturbance. Moreover, the approach makes it possible to explore high-dimensional sparse preference distributions and their linkage to individual specific characteristics, whic

preprint2020arXiv

Autoencoder-based time series clustering with energy applications

Time series clustering is a challenging task due to the specific nature of the data. Classical approaches do not perform well and need to be adapted either through a new distance measure or a data transformation. In this paper we investigate the combination of a convolutional autoencoder and a k-medoids algorithm to perfom time series clustering. The convolutional autoencoder allows to extract meaningful features and reduce the dimension of the data, leading to an improvement of the subsequent clustering. Using simulation and energy related data to validate the approach, experimental results show that the clustering is robust to outliers thus leading to finer clusters than with standard methods.

preprint2021arXiv

Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions

Limited data access is a longstanding barrier to data-driven research and development in the networked systems community. In this work, we explore if and how generative adversarial networks (GANs) can be used to incentivize data sharing by enabling a generic framework for sharing synthetic datasets with minimal expert knowledge. As a specific target, our focus in this paper is on time series datasets with metadata (e.g., packet loss rate measurements with corresponding ISPs). We identify key challenges of existing GAN approaches for such workloads with respect to fidelity (e.g., long-term dependencies, complex multidimensional relationships, mode collapse) and privacy (i.e., existing guarantees are poorly understood and can sacrifice fidelity). To improve fidelity, we design a custom workflow called DoppelGANger (DG) and demonstrate that across diverse real-world datasets (e.g., bandwidth measurements, cluster requests, web sessions) and use cases (e.g., structural characterization, predictive modeling, algorithm comparison), DG achieves up to 43% better fidelity than baseline models. Although we do not resolve the privacy problem in this work, we identify fundamental challenges with both classical notions of privacy and recent advances to improve the privacy properties of GANs, and suggest a potential roadmap for addressing these challenges. By shedding light on the promise and challenges, we hope our work can rekindle the conversation on workflows for data sharing.

preprint2015arXiv

Reliable ABC model choice via random forests

Approximate Bayesian computation (ABC) methods provide an elaborate approach to Bayesian inference on complex models, including model choice. Both theoretical arguments and simulation experiments indicate, however, that model posterior probabilities may be poorly evaluated by standard ABC techniques. We propose a novel approach based on a machine learning tool named random forests to conduct selection among the highly complex models covered by ABC algorithms. We thus modify the way Bayesian model selection is both understood and operated, in that we rephrase the inferential goal as a classification problem, first predicting the model that best fits the data with random forests and postponing the approximation of the posterior probability of the predicted MAP for a second stage also relying on random forests. Compared with earlier implementations of ABC model choice, the ABC random forest approach offers several potential improvements: (i) it often has a larger discriminative power among the competing models, (ii) it is more robust against the number and choice of statistics summarizing the data, (iii) the computing effort is drastically reduced (with a gain in computation efficienc

preprint2023arXiv

On the Susceptibility and Robustness of Time Series Models through Adversarial Attack and Defense

Under adversarial attacks, time series regression and classification are vulnerable. Adversarial defense, on the other hand, can make the models more resilient. It is important to evaluate how vulnerable different time series models are to attacks and how well they recover using defense. The sensitivity to various attacks and the robustness using the defense of several time series models are investigated in this study. Experiments are run on seven-time series models with three adversarial attacks and one adversarial defense. According to the findings, all models, particularly GRU and RNN, appear to be vulnerable. LSTM and GRU also have better defense recovery. FGSM exceeds the competitors in terms of attacks. PGD attacks are more difficult to recover from than other sorts of attacks.

preprint2016arXiv

Estimation from Indirect Supervision with Linear Moments

In structured prediction problems where we have indirect supervision of the output, maximum marginal likelihood faces two computational obstacles: non-convexity of the objective and intractability of even a single gradient computation. In this paper, we bypass both obstacles for a class of what we call linear indirectly-supervised problems. Our approach is simple: we solve a linear system to estimate sufficient statistics of the model, which we then use to estimate parameters via convex optimization. We analyze the statistical properties of our approach and show empirically that it is effective in two settings: learning with local privacy constraints and learning from low-cost count-based annotations.

preprint2013arXiv

Minimum Encoding Approaches for Predictive Modeling

We analyze differences between two information-theoretically motivated approaches to statistical inference and model selection: the Minimum Description Length (MDL) principle, and the Minimum Message Length (MML) principle. Based on this analysis, we present two revised versions of MML: a pointwise estimator which gives the MML-optimal single parameter model, and a volumewise estimator which gives the MML-optimal region in the parameter space. Our empirical results suggest that with small data sets, the MDL approach yields more accurate predictions than the MML estimators. The empirical results also demonstrate that the revised MML estimators introduced here perform better than the original MML estimator suggested by Wallace and Freeman.

preprint2026arXiv

Efficient Content-based Recommendation Model Training via Noise-aware Coreset Selection

Content-based recommendation systems (CRSs) utilize content features to predict user-item interactions, serving as essential tools for helping users navigate information-rich web services. However, ensuring the effectiveness of CRSs requires large-scale and even continuous model training to accommodate diverse user preferences, resulting in significant computational costs and resource demands. A promising approach to this challenge is coreset selection, which identifies a small but representative subset of data samples that preserves model quality while reducing training overhead. Yet, the selected coreset is vulnerable to the pervasive noise in user-item interactions, particularly when it is minimally sized. To this end, we propose Noise-aware Coreset Selection (NaCS), a specialized framework for CRSs. NaCS constructs coresets through submodular optimization based on training gradients, while simultaneously correcting noisy labels using a progressively trained model. Meanwhile, we refine the selected coreset by filtering out low-confidence samples through uncertainty quantification, thereby avoid training with unreliable interactions. Through extensive experiments, we show that Na

preprint2026arXiv

Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road

Recent progress in large language models has led to the emergence of reasoning models, which have shown strong performance on complex tasks through specialized fine-tuning procedures. While these methods reliably improve pass@1 accuracy, prior works have observed that they show a coverage shrinkage behavior, where pass@k degrades relative to the base model. In this paper, we investigate the reasoning shrinkage arise under SFT-based post-training. We hypothesize that this behavior is driven by properties of the fine-tuning data, specifically related to decision points or "forks in the road" scenarios where model faces indecipherable patterns with multiple valid reasoning paths. To test this hypothesis, we design controlled case studies that simulate such decision-point settings, spanning indecipherable nodes in graph branching, and reasoning modes. By tracking post-training dynamics in these settings, we find that the shrinkage phenomenon is tightly correlated with the prevalence of decision-point scenarios in the training data. We also demonstrate that this shrinkage behavior can be partially mitigated through targeted data synthesis design of decision-points, and a more systematic diversity-encouraging decoding mechanism. Our findings identify data-centric factors as a key driver of shrinkage in reasoning models and highlight diversity-aware designs as an effective lever for controlling it.

preprint2026arXiv

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited

Behavior Foundation Models (BFMs) enable scalable imitation learning (IL) by pretraining task-agnostic representations that can be rapidly adapted to new tasks. However, existing BFMs assume fixed environment dynamics, limiting their robustness under real-world shifts such as changes in friction, actuation, or sensor noise. We address this by formulating BFM task-inference as a robust minimax optimization problem, enabling adaptation to worst-case dynamics perturbations without modifying pretraining. To the best of our knowledge, this is the first BFM-based framework that achieves robustness to dynamics shifts while relying solely on offline data from a single nominal environment. Our approach significantly outperforms standard BFM and robust offline IL baselines under dynamics shifts. These results demonstrate that robust policy can be achieved entirely at task-inference time, improving the practicality of BFMs in dynamic settings.

preprint2022arXiv

Lensing Machines: Representing Perspective in Latent Variable Models

Many datasets represent a combination of different ways of looking at the same data that lead to different generalizations. For example, a corpus with examples generated by different people may be mixtures of many perspectives and can be viewed with different perspectives by others. It isnt always possible to represent the viewpoints by a clean separation, in advance, of examples representing each viewpoint and train a separate model for each viewpoint. We introduce lensing, a mixed initiative technique to extract lenses or mappings between machine learned representations and perspectives of human experts, and to generate lensed models that afford multiple perspectives of the same dataset. We apply lensing for two classes of latent variable models: a mixed membership model, a matrix factorization model in the context of two mental health applications, and we capture and imbue the perspectives of clinical psychologists into these models. Our work shows the benefits of the machine learning practitioner formally incorporating the perspective of a knowledgeable domain expert into their models rather than estimating unlensed models themselves in isolation.

preprint2020arXiv

Excessive Invariance Causes Adversarial Vulnerability

Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs. One core idea of adversarial example research is to reveal neural network errors under such distribution shifts. We decompose these errors into two complementary sources: sensitivity and invariance. We show deep networks are not only too sensitive to task-irrelevant changes of their input, as is well-known from epsilon-adversarial examples, but are also too invariant to a wide range of task-relevant changes, thus making vast regions in input space vulnerable to adversarial attacks. We show such excessive invariance occurs across various tasks and architecture types. On MNIST and ImageNet one can manipulate the class-specific content of almost any image without changing the hidden activations. We identify an insufficiency of the standard cross-entropy loss as a reason for these failures. Further, we extend this objective based on an information-theoretic analysis so it encourages the model to consider all task-dependent features in its decision. This provides the first approach tailored explicitly to overcome excessive invariance and resulting vulnerabilities.

preprint2026arXiv

Wide Neural Networks as a Baseline for the Computational No-Coincidence Conjecture

We establish that randomly initialized neural networks, with large width and a natural choice of hyperparameters, have nearly independent outputs exactly when their activation function is nonlinear with zero mean under the Gaussian measure: $\mathbb{E}_{z \sim \mathcal{N}(0,1)}[σ(z)]=0$. For example, this includes ReLU and GeLU with an additive shift, as well as tanh, but not ReLU or GeLU by themselves. Because of their nearly independent outputs, we propose neural networks with zero-mean activation functions as a promising candidate for the Alignment Research Center's computational no-coincidence conjecture -- a conjecture that aims to measure the limits of AI interpretability.

preprint2026arXiv

Reasoning Distillation for Lightweight Automated Program Repair

We study whether lightweight symbolic reasoning supervision can improve fix type classification in compact automated program repair models. Small code models are attractive for resource-constrained settings, but they typically produce only a single prediction, making it unclear whether they learn meaningful program structure or rely on shallow correlations. We propose a reasoning distillation approach in which a large teacher model provides structured symbolic reasoning tags alongside fix-type labels. These tags capture high-level causal properties of bugs without relying on free-form explanations. We train a CodeT5-based student model under label-only and reasoning-distilled settings on the IntroClass benchmark. Reasoning supervision consistently improves macro averaged performance, particularly on less frequent bug categories, without increasing model size or complexity. We further analyze the relationship between reasoning accuracy and fix-type prediction, showing that correct reasoning traces strongly correlate with correct predictions, while not fully determining them. Our results suggest that symbolic reasoning distillation is a practical way to improve interpretability and r

preprint2014arXiv

Incremental Clustering: The Case for Extra Clusters

The explosion in the amount of data available for analysis often necessitates a transition from batch to incremental clustering methods, which process one element at a time and typically store only a small subset of the data. In this paper, we initiate the formal analysis of incremental clustering methods focusing on the types of cluster structure that they are able to detect. We find that the incremental setting is strictly weaker than the batch model, proving that a fundamental class of cluster structures that can readily be detected in the batch setting is impossible to identify using any incremental method. Furthermore, we show how the limitations of incremental clustering can be overcome by allowing additional clusters.

preprint2020arXiv

Balanced k-Means Clustering on an Adiabatic Quantum Computer

Adiabatic quantum computers are a promising platform for approximately solving challenging optimization problems. We present a quantum approach to solving the balanced $k$-means clustering training problem on the D-Wave 2000Q adiabatic quantum computer. Existing classical approaches scale poorly for large datasets and only guarantee a locally optimal solution. We show that our quantum approach better targets the global solution of the training problem, while achieving better theoretic scalability on large datasets. We test our quantum approach on a number of small problems, and observe clustering performance similar to the best classical algorithms.

preprint2022arXiv

Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks

With the rise of deep neural networks, the challenge of explaining the predictions of these networks has become increasingly recognized. While many methods for explaining the decisions of deep neural networks exist, there is currently no consensus on how to evaluate them. On the other hand, robustness is a popular topic for deep learning research; however, it is hardly talked about in explainability until very recently. In this tutorial paper, we start by presenting gradient-based interpretability methods. These techniques use gradient signals to assign the burden of the decision on the input features. Later, we discuss how gradient-based methods can be evaluated for their robustness and the role that adversarial robustness plays in having meaningful explanations. We also discuss the limitations of gradient-based methods. Finally, we present the best practices and attributes that should be examined before choosing an explainability method. We conclude with the future directions for research in the area at the convergence of robustness and explainability.

preprint2012arXiv

Identifying confounders using additive noise models

We propose a method for inferring the existence of a latent common cause ('confounder') of two observed random variables. The method assumes that the two effects of the confounder are (possibly nonlinear) functions of the confounder plus independent, additive noise. We discuss under which conditions the model is identifiable (up to an arbitrary reparameterization of the confounder) from the joint distribution of the effects. We state and prove a theoretical result that provides evidence for the conjecture that the model is generically identifiable under suitable technical conditions. In addition, we propose a practical method to estimate the confounder from a finite i.i.d. sample of the effects and illustrate that the method works well on both simulated and real-world data.