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