BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Xiang Cheng

Xiang Cheng contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial Intelligencecond-mat.softeess.SPMachine LearningComputation and Languagephysics.flu-dynDatabasesBiological PhysicsComputationcond-mat.mtrl-scicond-mat.stat-mechCryptography and SecurityData Structures and AlgorithmsGenomicsmath.PR

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
20works
0followers
15topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

20 published item(s)

preprint2026arXiv

AMAP Agentic Planning Technical Report

We present STAgent, an agentic large language model tailored for spatio-temporal understanding, designed to solve complex tasks such as constrained point-of-interest discovery and itinerary planning. STAgent is a specialized model capable of interacting with ten distinct tools within spatio-temporal scenarios, enabling it to explore, verify, and refine intermediate steps during complex reasoning. Notably, STAgent effectively preserves its general capabilities. We empower STAgent with these capabilities through three key contributions: (1) a stable tool environment that supports over ten domain-specific tools, enabling asynchronous rollout and training; (2) a hierarchical data curation framework that identifies high-quality data like a needle in a haystack, curating high-quality queries by retaining less than 1\% of the raw data, emphasizing both diversity and difficulty; and (3) a cascaded training recipe that starts with a seed SFT stage acting as a guardian to measure query difficulty, followed by a second SFT stage fine-tuned on queries with high certainty, and an ultimate RL stage that leverages data of low certainty. Initialized with Qwen3-30B-A3B to establish a strong SFT foundation and leverage insights into sample difficulty, STAgent yields promising performance on TravelBench while maintaining its general capabilities across a wide range of general benchmarks, thereby demonstrating the effectiveness of our proposed agentic model.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger external teacher. Yet in math reasoning the gains are inconsistent, even when the same approach succeeds elsewhere. A pointwise mutual information analysis traces the failure to the privileged context itself: it inflates the teacher's confidence on tokens already implied by the solution (structural connectives, verifiable claims) and deflates it on deliberation tokens ("Wait", "Let", "Maybe") that drive multi-step search. We propose Anti-Self-Distillation (AntiSD), which ascends a divergence between student and teacher rather than descending it: this reverses the per-token sign and yields a naturally bounded advantage in one step. An entropy-triggered gate disables the term once the teacher entropy collapses, completing a drop-in replacement for default self-distillation. Across five models from 4B to 30B parameters on math reasoning benchmarks, AntiSD reaches the GRPO baseline's accuracy in 2 to 10x fewer training steps and improves final accuracy by up to 11.5 points. AntiSD opens a path to scalable self-improvement, where a language model bootstraps its own reasoning through its training signal.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation

On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback to serve as its own teacher, providing dense token-level rewards without external teacher models or step-level annotations. Despite its empirical success, what this reward actually measures and what kind of credit it assigns remain unclear. Under a posterior-compatibility interpretation of feedback conditioning, standard in the implicit-reward literature, we show that the self-distillation token reward is a Bayesian filtering increment whose trajectory sum is exactly the pointwise mutual information between the response and the feedback given the input. This pMI can be raised by input-specific reasoning or by input-generic shortcuts, so we further decompose the teacher log-probability along the input axis. Based on this analysis, we propose CREDIT (Contrastive REward from DIsTillation), which isolates the input-specific component with a batch-contrastive baseline. At the sequence level, CREDIT is a teacher-side surrogate for a contrastive pMI objective that also penalizes responses remaining likely under unrelated inputs. Across coding, scientific reasoning, and tool-use benchmarks on two model families, CREDIT delivers the strongest aggregate performance at negligible additional compute.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

GP-DHT: A Dual-Head Transformer with Contras-tive Learning for Predicting Gene Regulatory Rela-tionships across Species from Single-Cell Data

Gene regulatory networks (GRNs) are essential for understanding cell fate decisions and disease mechanisms, yet cross-species GRN inference from single-cell RNA-seq data remains challenging due to noise, sparsity, and cross-species distribution shifts. We propose GP-DHT (GenePair DualHeadTransformer), a cross-species single-cell GRN inference framework that models genes and cells in a heterogeneous graph with multi-level expression relations and learns structured regulatory representations via multi-relational graph attention. A dual-head Transformer further captures local gene pair regulatory dependencies and global cross-cell interaction patterns. To improve robustness under sparse and cross-species settings, GP-DHT introduces gene pair level supervised contrastive learning. Experiments on seven BEELINE benchmark datasets show consistent gains over representative baselines, improving AUROC and AUPRC by approximately 5 to 7 percent on most datasets. GP-DHT also recovers known regulatory modules and helps distinguish conserved from species-specific regulations.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Inertia-Dilatancy Interplay Governs Shear-Thickening Drop Impact

Combining high-speed photography with direct force measurements, we investigate the impact dynamics of drops of cornstarch-water mixtures -- a premier example of shear-thickening fluids -- across a wide range of impact conditions. Our study identifies three distinct impact regimes. In addition to the liquid-like and solid-like behaviors generally expected for the impact-induced response of shear-thickening fluids, we uncover a counterintuitive regime in which high-concentration cornstarch-water mixtures display a liquid-like response at the onset of impact when shear rates are high and only transition to a solid-like behavior at later times as shear rates reduce. By integrating the classic drop-impact theory with the Reynolds-Darcy mechanism for dilatancy, we develop a unified model that quantitatively describes the impact dynamics of shear-thickening drops across all regimes. Our work reveals the unexpected response of shear-thickening fluids to ultra-fast deformation and advances fundamental understanding of drop impact for complex fluids.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Large Wireless Foundation Models: Stronger over Bigger

AI-communication integration is widely regarded as a core enabling technology for 6G. Most existing AI-based physical-layer designs rely on task-specific models that are separately tailored to individual modules, resulting in poor generalization. In contrast, communication systems are inherently general-purpose and should support broad applicability and robustness across diverse scenarios. Foundation models offer a promising solution through strong reasoning and generalization, yet wireless-system constraints hinder a direct transfer of large language model (LLM)-style success to the wireless domain. Therefore, we introduce the concept of large wireless foundation models (LWFMs) and present a novel framework for empowering the physical layer with foundation models under wireless constraints. Specifically, we propose two paradigms for realizing LWFMs, including leveraging existing general-purpose foundation models and building novel wireless foundation models. Based on recent progress, we distill two roadmaps for each paradigm and formulate design principles under wireless constraints. We further provide case studies of LWFM-empowered wireless systems to intuitively validate their advantages. Finally, we characterize the notion of "large" in LWFMs through a multidimensional analysis of existing work and outline promising directions for future research.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning

A central challenge in reinforcement learning (RL) is to learn models that generalize beyond the tasks on which they are trained, a goal traditionally pursued through multi-task and meta RL. Recently, transformer architectures have emerged as a promising approach, enabling adaptation to new tasks via in-context learning without explicit parameter updates. From a functional perspective, a transformer can be viewed as a functional operator that maps a context to a task-specific function. It is thus fundamental to understand and design this operator to support stronger generalization in RL. In this work, we address this resulting question of generalization from a kernel-based perspective by establishing a connection between non-linear transformers and kernel-based temporal difference learning. By interpreting the transformer as performing regression in a Reproducing Kernel Hilbert Space (RKHS), we show that value functions from different domains can be represented using a shared set of weights, provided they lie within the same RKHS. Experiments on multiple MetaWorld domains support this interpretation, demonstrating convergence of the temporal-difference objective.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot

In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs), and recent studies introduce Chain-of-Thought (CoT) to exemplars of ICL to enhance the reasoning capability, especially in mathematics tasks. However, given the continuous advancement of model capabilities, it remains unclear whether CoT exemplars still benefit recent, stronger models in such tasks. Through systematic experiments, we find that for recent strong models such as the Qwen2.5 series, adding traditional CoT exemplars does not improve reasoning performance compared to Zero-Shot CoT. Instead, their primary function is to align the output format with human expectations. We further investigate the effectiveness of enhanced CoT exemplars, constructed using answers from advanced models such as \texttt{Qwen2.5-Max} and \texttt{DeepSeek-R1}. Experimental results indicate that these enhanced exemplars still fail to improve the model's reasoning performance. Further analysis reveals that models tend to ignore the exemplars and focus primarily on the instructions, leading to no observable gain in reasoning ability. Overall, our findings highlight the limitations of the current ICL+CoT framework in mathematical reasoning, calling for a re-examination of the ICL paradigm and the definition of exemplars.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Synesthesia of Machines (SoM)-Aided Online FDD Precoding via Heterogeneous Multi-Modal Sensing: A Vertical Federated Learning Approach

This paper investigates a heterogeneous multi-vehicle, multi-modal sensing (H-MVMM) aided online precoding problem. The proposed H-MVMM scheme utilizes a vertical federated learning (VFL) framework to minimize pilot sequence length and optimize the sum rate. This offers a promising solution for reducing latency in frequency division duplexing systems. To achieve this, three preprocessing modules are designed to transform raw sensory data into informative representations relevant to precoding. The approach effectively addresses local data heterogeneity arising from diverse on-board sensor configurations through a well-structured VFL training procedure. Additionally, a label-free online model updating strategy is introduced, enabling the H-MVMM scheme to adapt its weights flexibly. This strategy features a pseudo downlink channel state information label simulator (PCSI-Simulator), which is trained using a semi-supervised learning (SSL) approach alongside an online loss function. Numerical results show that the proposed method can closely approximate the performance of traditional optimization techniques with perfect channel state information, achieving a significant 90.6\% reduction in pilot sequence length.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Tiny-WiFo: A Lightweight Wireless Foundation Model for Channel Prediction via Multi-Component Adaptive Knowledge Distillation

The massive scale of Wireless Foundation Models (FMs) hinders their real-time deployment on edge devices. This letter moves beyond standard knowledge distillation by introducing a novel Multi-Component Adaptive Knowledge Distillation (MCAKD) framework. Key innovations include a Cross-Attention-Based Knowledge Selection (CA-KS) module that selectively identifies critical features from the teacher model, and an Autonomous Learning-Passive Learning (AL-PL) strategy that balances knowledge transfer with independent learning to achieve high training efficiency at a manageable computational cost. When applied to the WiFo FM, the distilled Tiny-WiFo model, with only 5.5M parameters, achieves a 1.6 ms inference time while retaining over 98% of WiFo's performance and its crucial zero-shot generalization capability, making real-time FM deployment viable.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

WiFo-E: A Scalable Wireless Foundation Model for End-to-End FDD Precoding in Communication Networks

Accurate precoding in massive multiple-input multiple-output (MIMO) frequency-division duplexing (FDD) systems relies on efficient channel state information (CSI) acquisition. End-to-end learning frameworks improve performance by jointly optimizing this process, but they lack scalability and fail to generalize across different system configurations, such as varying numbers of antennas and users. To overcome this limitation, we introduce WiFo-E, a wireless foundation model designed for scalable end-to-end precoding. WiFo-E employs multi-task pretraining on a diverse set of configurations to learn transferable representations of underlying wireless principles. Central to the model is a sparse Mixture-of-Experts (MoE) Transformer architecture, which mitigates task interference and enhances training efficiency by activating specialized parameter subsets adaptively. Extensive simulations demonstrate that WiFo-E outperforms conventional per-configuration training and shows strong generalization to unseen system configurations, providing a flexible and efficient foundation for adaptive massive MIMO precoding.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

WiFo-MUD: Wireless Foundation Model for Heterogeneous Multi-User Demodulator

Multi-user signal demodulation is critical to wireless communications, directly impacting transmission reliability and efficiency. However, existing demodulators underperform in generic multi-user environments: classical demodulators struggle to balance accuracy and complexity, while deep learning-based methods lack adaptability under heterogeneous configurations. Although diffusion models have been introduced for demodulation, their flexibility remains limited for practical use. To address these issues, this work proposes WiFo-MUD, a universal diffusion-based foundation model for multi-user demodulation. The model aligns inter-user signal-to-noise ratio imbalance and performs conditional denoising via a customized backbone. Furthermore, a communication-aware consistency distillation method and a dynamic user-grouping strategy are devised to enhance inference. WiFo-MUD achieves state-of-the-art results on large-scale heterogeneous datasets, demonstrating efficient inference and strong generalization across varying system configurations.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

LLMs for Explainable Business Decision-Making: A Reinforcement Learning Fine-Tuning Approach

Artificial Intelligence (AI) models increasingly drive high-stakes consumer interactions, yet their decision logic often remains opaque. Prevailing explainable AI techniques rely on post hoc numerical feature attributions, which fail to provide coherent narratives behind model decisions. Large language models (LLMs) present an opportunity to generate natural-language explanations, but three design challenges remain unresolved: explanations must be both decision-correct and faithful to the factors that drive the prediction; they should be able to serve multiple audiences without shifting the underlying decision rule; and they should be trained in a label-efficient way that does not depend on large corpora of human-scored explanations. To address these challenges, we introduce LEXMA (LLM-based EXplanations for Multi-Audience decisions), a reinforcement-learning-based fine-tuning framework that produces narrative-driven, audience-appropriate explanations. LEXMA combines reflection-augmented supervised fine-tuning with two stages of Group Relative Policy Optimization (GRPO). Specifically, it fine-tunes two separate parameter sets to improve decision correctness and satisfy stylistic requirements for different audiences, using reward signals that do not rely on human-annotated explanations. We instantiate LEXMA in the context of mortgage approval decisions. Results demonstrate that LEXMA yields significant improvements in predictive performance compared with other LLM baselines. Moreover, human evaluations show that expert-facing explanations generated by our approach are more risk-focused, and consumer-facing explanations are clearer, more actionable, and more polite. Our study contributes a cost-efficient, systematic LLM fine-tuning approach to enhance explanation quality for business decisions, offering strong potential for scalable deployment of transparent AI systems.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Stress distribution and surface shock wave of drop impact

Drop impact causes severe surface erosion, dictating many important natural, environmental and engineering processes and calling for substantial prevention and preservation efforts. Nevertheless, despite extensive studies on the kinematic features of impacting drops over the last two decades, the dynamic process that leads to the drop-impact erosion is still far from clear. Here, we develop a method of high-speed stress microscopy, which measures the key dynamic properties of drop impact responsible for erosion, i.e., the shear stress and pressure distributions of impacting drops, with unprecedented spatiotemporal resolutions. Our experiments reveal the fast propagation of self-similar noncentral stress maxima underneath impacting drops and quantify the shear force on impacted substrates. Moreover, we examine the deformation of elastic substrates under impact and uncover impact-induced surface shock waves. Our study opens the door for quantitative measurements of the impact stress of liquid drops and sheds light on the origin of low-speed drop-impact erosion.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The colloidal nature of complex fluids leads to enhanced motility of flagellated bacteria

The natural habitats of microorganisms in the human microbiome and ocean and soil ecosystems are full of colloids and macromolecules, which impart non-Newtonian flow properties drastically affecting the locomotion of swimming microorganisms. Although the low-Reynolds-number hydrodynamics of the swimming of flagellated bacteria in simple Newtonian fluids has been well developed, our understanding of bacterial motility in complex non-Newtonian fluids is still primitive. Even after six decades of research, fundamental questions about the nature and origin of bacterial motility enhancement in polymer solutions are still under debate. Here, we study the motility of flagellated bacteria in colloidal suspensions of varying sizes and volume fractions. We find that bacteria in dilute colloidal suspensions display quantitatively the same motile behaviors as those in dilute polymer solutions, where a universal particle-size-dependent motility enhancement up to 80% is uncovered, accompanied by strong suppression of bacterial wobbling. By virtue of the well-controlled size and the hard-sphere nature of colloids, the finding not only resolves the long-standing controversy over bacterial motility enhancement in complex fluids but also challenges all the existing theories using polymer dynamics to address the swimming of flagellated bacteria in dilute polymer solutions. We further develop a simple physical model incorporating the colloidal nature of complex fluids, which quantitatively explains bacterial wobbling dynamics and mobility enhancement in both colloidal and polymeric fluids. Our study sheds light on the puzzling motile behaviors of bacteria in complex fluids relevant to a wide range of microbiological processes and provides a cornerstone in engineering bacterial swimming in complex environments.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Tuning the rheology and microstructure of particle-laden fluid interfaces with Janus particles

Hypothesis: Particle-laden fluid interfaces are the central component of many natural and engineering systems. Understanding the mechanical properties and improving the stability of such interfaces are of great practical importance. Janus particles, a special class of heterogeneous colloids, might be utilized as an effective surface-active agent to control the assembly and interfacial rheology of particle-laden fluid interfaces. Experiments: Using a custom-built interfacial stress rheometer, we explore the effect of Janus particle additives on the interfacial rheology and microscopic structure of particle-laden fluid interfaces. Findings: We find that the addition of a small amount of platinum-polystyrene (Pt-PS) Janus particles within a monolayer of PS colloids (1:40 number ratio) can lead to more than an order-of-magnitude increase in surface moduli with enhanced elasticity, which greatly improves the stability of the interface. This drastic change in interfacial rheology is associated with the formation of local particle clusters surrounding each Janus particle. We further explain the origin of local particle clusters by considering the interparticle interactions at the interface. Our experiments reveal the effect of local particle structures on the macroscopic rheological behaviors of particle monolayers and demonstrate a new way to tune the microstructure and mechanical properties of particle-laden fluid interfaces.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Auto-FuzzyJoin: Auto-Program Fuzzy Similarity Joins Without Labeled Examples

Fuzzy similarity join is an important database operator widely used in practice. So far the research community has focused exclusively on optimizing fuzzy join \textit{scalability}. However, practitioners today also struggle to optimize fuzzy-join \textit{quality}, because they face a daunting space of parameters (e.g., distance-functions, distance-thresholds, tokenization-options, etc.), and often have to resort to a manual trial-and-error approach to program these parameters in order to optimize fuzzy-join quality. This key challenge of automatically generating high-quality fuzzy-join programs has received surprisingly little attention thus far. In this work, we study the problem of "auto-program" fuzzy-joins. Leveraging a geometric interpretation of distance-functions, we develop an unsupervised \textsc{Auto-FuzzyJoin} framework that can infer suitable fuzzy-join programs on given input tables, without requiring explicit human input such as labeled training data. Using \textsc{Auto-FuzzyJoin}, users only need to provide two input tables $L$ and $R$, and a desired precision target $τ$ (say 0.9). \textsc{Auto-FuzzyJoin} leverages the fact that one of the input is a reference table to automatically program fuzzy-joins that meet the precision target $τ$ in expectation, while maximizing fuzzy-join recall (defined as the number of correctly joined records). Experiments on both existing benchmarks and a new benchmark with 50 fuzzy-join tasks created from Wikipedia data suggest that the proposed \textsc{Auto-FuzzyJoin} significantly outperforms existing unsupervised approaches, and is surprisingly competitive even against supervised approaches (e.g., Magellan and DeepMatcher) when 50\% of ground-truth labels are used as training data.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Imaging the emergence of bacterial turbulence: phase diagram and transition kinetics

We experimentally study the emergence of collective bacterial swimming, a phenomenon often referred to as bacterial turbulence. A phase diagram of the flow of 3D E. coli suspensions spanned by bacterial concentration, the swimming speed of bacteria and the number fraction of active swimmers is systematically mapped, which shows quantitative agreement with kinetic theories and demonstrates the dominant role of hydrodynamic interactions in bacterial collective swimming. More importantly, we trigger bacterial turbulence by suddenly increasing the swimming speed of light-powered bacteria and image the transition to the turbulence in real time. Our experiments identify two unusual kinetic pathways, i.e., the one-step transition with long incubation periods near the phase boundary and the two-step transition driven by long-wavelength instabilities deep inside the turbulent phase. Our study provides not only a quantitative verification of existing theories, but also new insights into interparticle interactions and transition kinetics of bacterial turbulence.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Answering Multi-Dimensional Range Queries under Local Differential Privacy

In this paper, we tackle the problem of answering multi-dimensional range queries under local differential privacy. There are three key technical challenges: capturing the correlations among attributes, avoiding the curse of dimensionality, and dealing with the large domains of attributes. None of the existing approaches satisfactorily deals with all three challenges. Overcoming these three challenges, we first propose an approach called Two-Dimensional Grids (TDG). Its main idea is to carefully use binning to partition the two-dimensional (2-D) domains of all attribute pairs into 2-D grids that can answer all 2-D range queries and then estimate the answer of a higher dimensional range query from the answers of the associated 2-D range queries. However, in order to reduce errors due to noises, coarse granularities are needed for each attribute in 2-D grids, losing fine-grained distribution information for individual attributes. To correct this deficiency, we further propose Hybrid-Dimensional Grids (HDG), which also introduces 1-D grids to capture finer-grained information on distribution of each individual attribute and combines information from 1-D and 2-D grids to answer range queries. To make HDG consistently effective, we provide a guideline for properly choosing granularities of grids based on an analysis of how different sources of errors are impacted by these choices. Extensive experiments conducted on real and synthetic datasets show that HDG can give a significant improvement over the existing approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Sharp convergence rates for Langevin dynamics in the nonconvex setting

We study the problem of sampling from a distribution $p^*(x) \propto \exp\left(-U(x)\right)$, where the function $U$ is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially nonconvex inside this ball. We study both overdamped and underdamped Langevin MCMC and establish upper bounds on the number of steps required to obtain a sample from a distribution that is within $ε$ of $p^*$ in $1$-Wasserstein distance. For the first-order method (overdamped Langevin MCMC), the iteration complexity is $\tilde{\mathcal{O}}\left(e^{cLR^2}d/ε^2\right)$, where $d$ is the dimension of the underlying space. For the second-order method (underdamped Langevin MCMC), the iteration complexity is $\tilde{\mathcal{O}}\left(e^{cLR^2}\sqrt{d}/ε\right)$ for an explicit positive constant $c$. Surprisingly, the iteration complexity for both these algorithms is only polynomial in the dimension $d$ and the target accuracy $ε$. It is exponential, however, in the problem parameter $LR^2$, which is a measure of non-log-concavity of the target distribution.

0 citations0 reviewsNo code linkedOpen access