Niao He

8

Papers

19

Total Citations

Papers (8)

On the Crucial Role of Initialization for Matrix Factorization

Provable Maximum Entropy Manifold Exploration via Diffusion Models

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

Truly No-Regret Learning in Constrained MDPs

Scalable Neural Incentive Design with Parameterized Mean-Field Approximation

DPZero: Private Fine-Tuning of Language Models without Backpropagation

Automated Design of Affine Maximizer Mechanisms in Dynamic Settings

Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL