Wotao Yin

Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs ICML 2025 Scale Down to Speed Up: Dynamic Data Selection for Reinforcement Learning EMNLP 2025 BC-Prover: Backward Chaining Prover for Formal Theorem Proving EMNLP 2024 Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares ICML 2024 Efficient Algorithms for Sum-Of-Minimum Optimization ICML 2024 Rethinking the Capacity of Graph Neural Networks for Branching Strategy NeurIPS 2024 Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ICML 2024 Solving General Natural-Language-Description Optimization Problems with Large Language Models NAACL 2024 Alternating Projected SGD for Equality-constrained Bilevel Optimization AISTATS 2023 DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm ICML 2023 HeteRSGD: Tackling Heterogeneous Sampling Costs via Optimal Reweighted Stochastic Gradient Descent AISTATS 2023 On Representing Linear Programs by Graph Neural Networks ICLR 2023 On Representing Mixed-Integer Linear Programs by Graph Neural Networks ICLR 2023 Safeguarded Learned Convex Optimization AAAI 2023 Towards Constituting Mathematical Structures for Learning to Optimize ICML 2023 A Single-Timescale Method for Stochastic Bilevel Optimization AISTATS 2022 Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate NeurIPS 2022 FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting NeurIPS 2022 JFB: Jacobian-Free Backpropagation for Implicit Networks AAAI 2022 Learning to Optimize: A Primer and A Benchmark JMLR 2022 Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression NeurIPS 2022 Accelerating Gossip SGD with Periodic Global Averaging ICML 2021 An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders NeurIPS 2021 AutoBandit: A Meta Bandit Online Learning System IJCAI 2021 A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization ICML 2021 CADA: Communication-Adaptive Distributed Adam AISTATS 2021 Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems NeurIPS 2021 DecentLaM: Decentralized Momentum SGD for Large-Batch Deep Training ICCV 2021 Exponential Graph is Provably Efficient for Decentralized Deep Training NeurIPS 2021 Hyperparameter Tuning is All You Need for LISTA NeurIPS 2021 Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection NeurIPS 2021 Learning A Minimax Optimizer: A Pilot Study ICLR 2021 Provably Correct Optimization and Exploration with Non-linear Policies ICML 2021 An Improved Analysis of Stochastic Gradient Descent with Momentum NeurIPS 2020 An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods NeurIPS 2020 AsyncQVI: Asynchronous-Parallel Q-Value Iteration for Discounted Markov Decision Processes with Near-Optimal Sample Complexity AISTATS 2020 Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning NeurIPS 2020 A2BCD: Asynchronous Acceleration with Optimal Complexity ICLR 2019 Acceleration of SVRG and Katyusha X by Inexact Preconditioning ICML 2019 ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA ICLR 2019 Plug-and-Play Methods Provably Converge with Properly Trained Denoisers ICML 2019 Redundancy Techniques for Straggler Mitigation in Distributed Optimization and Learning JMLR 2019 Breaking the Span Assumption Yields Fast Finite-Sum Minimization NeurIPS 2018 LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning NeurIPS 2018 On Markov Chain Gradient Descent NeurIPS 2018 Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds NeurIPS 2018 Asynchronous Coordinate Descent under More Realistic Assumptions NeurIPS 2017 Straggler Mitigation in Distributed Optimization Through Data Encoding NeurIPS 2017 A Fast Hybrid Algorithm for Large-Scale -Regularized Logistic Regression JMLR 2010