Wotao Yin

papers

1,185

total citations

papers (16)

FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting

NEURIPS 2022arXiv

290

citations

An Improved Analysis of Stochastic Gradient Descent with Momentum

NEURIPS 2020arXiv

288

citations

An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods

NEURIPS 2020arXiv

124

citations

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

ICML 2024arXiv

107

citations

Exponential Graph is Provably Efficient for Decentralized Deep Training

NEURIPS 2021arXiv

107

citations

DecentLaM: Decentralized Momentum SGD for Large-Batch Deep Training

ICCV 2021arXiv

citations

Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection

NEURIPS 2021arXiv

citations

Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate

NEURIPS 2022arXiv

citations

Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression

NEURIPS 2022arXiv

citations

Hyperparameter Tuning is All You Need for LISTA

NEURIPS 2021arXiv

citations

An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders

NEURIPS 2021arXiv

citations

Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning

NEURIPS 2020arXiv

citations

Efficient Algorithms for Sum-Of-Minimum Optimization

ICML 2024arXiv

citations

Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares

ICML 2024arXiv

citations

Subsampled Ensemble Can Improve Generalization Tail Exponentially

NEURIPS 2025arXiv

citations

Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems

NEURIPS 2021

citations