979 citations · 1.6k across the 23 of their papers we have counts for
8 papers · 1 filter
Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement
Hui Yuan, Kaixuan Huang, Chengzhuo Ni +2
We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measur…
Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data
Minshuo Chen, Kaixuan Huang, Tuo Zhao +1
Diffusion models achieve state-of-the-art performance in various generation tasks. However, their theoretical foundations fall far behind. This paper studies score approximation, e…
Provably Efficient Reinforcement Learning for Online Adaptive Influence Maximization
Kaixuan Huang, Yu Wu, Xuezhou Zhang +4
Online influence maximization aims to maximize the influence spread of a content in a social network with unknown network model by selecting a few seed nodes. Recent studies follow…
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
Baihe Huang, Kaixuan Huang, Sham M. Kakade +4
Bandit problems with linear or concave reward have been extensively studied, but relatively few works have studied bandits with non-concave reward. This work considers a large fami…
A Short Note on the Relationship of Information Gain and Eluder Dimension
Kaixuan Huang, Sham M. Kakade, Jason D. Lee +1
Eluder dimension and information gain are two widely used methods of complexity measures in bandit and reinforcement learning. Eluder dimension was originally proposed as a general…
Going Beyond Linear RL: Sample Efficient Neural Function Approximation
Baihe Huang, Kaixuan Huang, Sham M. Kakade +4
Deep Reinforcement Learning (RL) powered by neural net approximation of the Q function has had enormous empirical success. While the theory of RL has traditionally focused on linea…
Fast Federated Learning in the Presence of Arbitrary Device Unavailability
Xinran Gu, Kaixuan Huang, Jingzhao Zhang +1
Federated Learning (FL) coordinates with numerous heterogeneous devices to collaboratively train a shared model while preserving user privacy. Despite its multiple advantages, FL f…
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? -- A Neural Tangent Kernel Perspective
Kaixuan Huang, Yuqing Wang, Molei Tao +1
Deep residual networks (ResNets) have demonstrated better generalization performance than deep feedforward networks (FFNets). However, the theory behind such a phenomenon is still…