α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Niao He
Niao He
23
papers
263
total citations
papers (23)
Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning
NEURIPS 2020
arXiv
59
citations
Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
NEURIPS 2023
arXiv
25
citations
Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization
NEURIPS 2022
arXiv
25
citations
Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization
NEURIPS 2022
arXiv
22
citations
Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions
NEURIPS 2022
arXiv
22
citations
DPZero: Private Fine-Tuning of Language Models without Backpropagation
ICML 2024
arXiv
22
citations
The Mean-Squared Error of Double Q-Learning
NEURIPS 2020
arXiv
19
citations
Truly No-Regret Learning in Constrained MDPs
ICML 2024
arXiv
16
citations
On the Crucial Role of Initialization for Matrix Factorization
ICLR 2025
arXiv
11
citations
Automated Design of Affine Maximizer Mechanisms in Dynamic Settings
AAAI 2024
arXiv
11
citations
Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
ICML 2024
arXiv
8
citations
On Imitation in Mean-field Games
NEURIPS 2023
arXiv
8
citations
Provable Maximum Entropy Manifold Exploration via Diffusion Models
ICML 2025
arXiv
7
citations
Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
ICML 2025
arXiv
4
citations
Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
NEURIPS 2023
arXiv
3
citations
Robust Knowledge Transfer in Tiered Reinforcement Learning
NEURIPS 2023
arXiv
1
citations
A Catalyst Framework for Minimax Optimization
NEURIPS 2020
0
citations
Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems
NEURIPS 2020
0
citations
Sharp Analysis of Stochastic Optimization under Global Kurdyka-Lojasiewicz Inequality
NEURIPS 2022
0
citations
On the Bias-Variance-Cost Tradeoff of Stochastic Optimization
NEURIPS 2021
0
citations
Scalable Neural Incentive Design with Parameterized Mean-Field Approximation
NEURIPS 2025
arXiv
0
citations
The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models
NEURIPS 2020
0
citations
A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms
NEURIPS 2020
0
citations