Author name cluster

Kevin Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

AAMAS Conference 2026 Conference Paper

Approximating Nash Equilibria in General-Sum Games via Meta-Learning

David Sychrovský
Christopher Solinas
Revan MacQueen
Kevin Wang
James R. Wright
Nathan R. Sturtevant
Michael Bowling

Nash equilibrium is perhaps the best-known solution concept in game theory. Such a solution assigns a strategy to each player which offers no incentive to unilaterally deviate. While a Nash equilibrium is guaranteed to always exist, the problem of finding one in general-sum games is PPAD-complete, generally considered intractable. Regret minimization is an efficient framework for approximatingNashequilibriaintwo-playerzero-sumgames. However, in general-sum games, such algorithms are only guaranteed to converge to a coarse-correlated equilibrium (CCE), a solution concept where players can correlate their strategies. In this work, we use meta-learning to minimize the correlations in strategies produced by a regret minimizer. This encourages the regret minimizer to find strategies that are closer to a Nash equilibrium. The meta-learned regret minimizer is still guaranteed to converge to a CCE, but we give a bound on the distance to Nash equilibrium in terms of our meta-loss. We evaluate our approach in general-sum imperfect information games. Our algorithms provide significantly betterapproximationsofNashequilibriathanstate-of-the-artregret minimization techniques.

PDF

NeurIPS Conference 2025 Conference Paper

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities

Kevin Wang
Ishaan Javali
Michał Bortkiewicz
Tomasz Trzcinski
Benjamin Eysenbach

Scaling up self-supervised learning has driven breakthroughs in language and vision, yet comparable progress has remained elusive in reinforcement learning (RL). In this paper, we study building blocks for self-supervised RL that unlock substantial improvements in scalability, with network depth serving as a critical factor. Whereas most RL papers in recent years have relied on shallow architectures (around 2 -- 5 layers), we demonstrate that increasing the depth up to 1024 layers can significantly boost performance. Our experiments are conducted in an unsupervised goal-conditioned setting, where no demonstrations or rewards are provided, so an agent must explore (from scratch) and learn how to maximize the likelihood of reaching commanded goals. Evaluated on simulated locomotion and manipulation tasks, our approach increases performance on the self-supervised contrastive RL algorithm by $2\times$ -- $50\times$, outperforming other goal-conditioned baselines. Increasing the model depth not only increases success rates but also qualitatively changes the behaviors learned.

PDF Details

JMLR Journal 2025 Journal Article

Deep Generative Models: Complexity, Dimensionality, and Approximation

Kevin Wang
Hongqian Niu
Yixin Wang
Didong Li

Generative networks have shown remarkable success in learning complex data distributions, particularly in generating high-dimensional data from lower-dimensional inputs. While this capability is well-documented empirically, its theoretical underpinning remains unclear. One common theoretical explanation appeals to the widely accepted manifold hypothesis, which suggests that many real-world datasets, such as images and signals, often possess intrinsic low-dimensional geometric structures. Under this manifold hypothesis, it is widely believed that to approximate a distribution on a $d$-dimensional Riemannian manifold, the latent dimension needs to be at least $d$ or $d+1$. In this work, we show that this requirement on the latent dimension is not necessary by demonstrating that generative networks can approximate distributions on $d$-dimensional Riemannian manifolds from inputs of any arbitrary dimension, even lower than $d$, taking inspiration from the concept of space-filling curves. This approach, in turn, leads to a super-exponential complexity bound of the deep neural networks through expanded neurons. Our findings thus challenge the conventional belief on the relationship between input dimensionality and the ability of generative networks to model data distributions. This novel insight not only corroborates the practical effectiveness of generative networks in handling complex data structures, but also underscores a critical trade-off between approximation error, dimensionality, and model complexity. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2025. ( edit, beta )

PDF Details

YNICL Journal 2025 Journal Article

Linked alterations in structure and autoimmunity biomarkers in remote mild-to-moderate TBI: A multi-modal brain imaging study

Abigail B. Waters
Samantha H. Penhale
Shoumi Sarkar
Somnath Datta
Damon G. Lamb
Claudia Robertson
Richard Rubenstein
Amy K. Wagner

BACKGROUND: There is significant heterogeneity in the recovery course from mild-to-moderate traumatic brain injury (mmTBI), with many individuals reporting cognitive symptoms during the chronic phase. Although blood-based biomarkers have been identified as a marker of injury severity in the acute phase, the relevance of candidate biomarkers in chronic mmTBI is less clear. Establishing links between blood-based biomarkers, neuroimaging, and cognitive performance is necessary to differentiate subphenotypes in chronic TBI and improve prognostic models. METHODS: Sixty Veterans and non-Veterans with mmTBI completed cognitive testing (WAIS-IV), MRI, and blood collection for blood-based CNS biomarker assessment for cross-sectional comparison. A data fusion technique (Linked Independent Component Analysis [LICA]) was used to simultaneously model structural variability across T1-weighted and diffusion-weighted MRI modalities. Blood serum samples were assayed using an ultrasensitive immunoassay using digital array technology to measure GFAP, NFL, total tau, and UCH-L1 protein levels. A correlation matrix was used to identify which LICA-derived MRI components were associated with (1) a blood-based biomarker, (2) a WAIS-IV index score and (3) clinical characteristics of TBI, using an effect-size cut-off. RESULTS: LICA-derived Component 4 was associated with a biomarker (UCH-L1), reduced processing speed, and the total number of TBIs. This component was characterized by increased mean diffusivity along the ventral surface of the frontal lobe and decreased fractional anisotropy in bilateral corticospinal tracts and cerebral peduncles. CONCLUSIONS: Our findings contribute to the larger body of literature examining the utility of biomarkers for chronic TBI and underscore the importance of examining heterogeneity within this population.

Details DOI

NeurIPS Conference 2024 Conference Paper

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS

Zhiwen Fan
Kevin Wang
Kairun Wen
Zehao Zhu
Dejia Xu
Zhangyang Wang

Recent advances in real-time neural rendering using point-based techniques have enabled broader adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting impose substantial storage overhead, as Structure-from-Motion (SfM) points can grow to millions, often requiring gigabyte-level disk space for a single unbounded scene. This growth presents scalability challenges and hinders splatting efficiency. To address this, we introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction, and applies a pruning and recovery process to reduce redundancy while preserving visual quality. Knowledge distillation and pseudo-view augmentation then transfer spherical harmonic coefficients to a lower degree, yielding compact representations. Gaussian Vector Quantization, based on each Gaussian’s global significance, further lowers bitwidth with minimal accuracy loss. LightGaussian achieves an average 15 times compression rate while boosting FPS from 144 to 237 within the 3D-GS framework, enabling efficient complex scene representation on the Mip-NeRF 360 and Tank & Temple datasets. The proposed Gaussian pruning approach is also adaptable to other 3D representations (e. g. , Scaffold-GS), demonstrating strong generalization capabilities.

PDF Details DOI

ICML Conference 2023 Conference Paper

Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation

Wenqing Zheng
S. P. Sharan
Ajay Kumar Jaiswal
Kevin Wang
Yihan Xi
Dejia Xu
Zhangyang Wang

For a complicated algorithm, its implementation by a human programmer usually starts with outlining a rough control flow followed by iterative enrichments, eventually yielding carefully generated syntactic structures and variables in a hierarchy. However, state-of-the-art large language models generate codes in a single pass, without intermediate warm-ups to reflect the structured thought process of "outline-then-detail". Inspired by the recent success of chain-of-thought prompting, we propose ChainCoder, a program synthesis language model that generates Python code progressively, i. e. from coarse to fine in multiple passes. We first decompose source code into layout frame components and accessory components via abstract syntax tree parsing to construct a hierarchical representation. We then reform our prediction target into a multi-pass objective, each pass generates a subsequence, which is concatenated in the hierarchy. Finally, a tailored transformer architecture is leveraged to jointly encode the natural language descriptions and syntactically aligned I/O data samples. Extensive evaluations show that ChainCoder outperforms state-of-the-arts, demonstrating that our progressive generation eases the reasoning procedure and guides the language model to generate higher-quality solutions. Our codes are available at: https: //github. com/VITA-Group/ChainCoder.

Details

ICRA Conference 2018 Conference Paper

Data-Driven Model Predictive Control of Autonomous Mobility-on-Demand Systems

Ramón Iglesias
Federico Rossi 0001
Kevin Wang
David Hallac
Jure Leskovec
Marco Pavone 0001

The goal of this paper is to present an end-to-end, data-driven framework to control Autonomous Mobility-on-Demand systems (AMoD, i. e. fleets of self-driving vehicles). We first model the AMoD system using a time-expanded network, and present a formulation that computes the optimal rebalancing strategy (i. e. , preemptive repositioning) and the minimum feasible fleet size for a given travel demand. Then, we adapt this formulation to devise a Model Predictive Control (MPC) algorithm that leverages short-term demand forecasts based on historical data to compute rebalancing strategies. Using simulations based on real customer data from DiDi Chuxing, we test the end-to-end performance of this controller with a state-of-the-art LSTM neural network to predict customer demand: we show that this approach scales very well for large systems (indeed, the computational complexity of the MPC algorithm does not depend on the number of customers and of vehicles in the system) and outperforms state-of-the-art rebalancing strategies by reducing the mean customer wait time by up to to 89. 6 %.

Details