6 papers
Path-Guided Particle-based Sampling
Mingzhou Fan, Ruida Zhou, Chao Tian +1
Particle-based Bayesian inference methods by sampling from a partition-free target (posterior) distribution, e.g., Stein variational gradient descent (SVGD), have attracted signifi…
An Information-Theoretic Approach to Understanding Transformers' In-Context Learning of Variable-Order Markov Chains
Ruida Zhou, Chao Tian, Suhas Diggavi
We study transformers' in-context learning of variable-length Markov chains (VOMCs), focusing on the finite-sample accuracy as the number of in-context examples increases. Compared…
Staggered Quantizers for Perfect Perceptual Quality: A Connection between Quantizers with Common Randomness and Without
Ruida Zhou, Chao Tian
The rate-distortion-perception (RDP) framework has attracted significant recent attention due to its application in neural compression. It is important to understand the underlying…
Provable Policy Gradient Methods for Average-Reward Markov Potential Games
Min Cheng, Ruida Zhou, P. R. Kumar +1
We study Markov potential games under the infinite horizon average reward criterion. Most previous studies have been for discounted rewards. We prove that both algorithms based on…
Weakly Private Information Retrieval from Heterogeneously Trusted Servers
Wenyuan Zhao, Yu-Shin Huang, Ruida Zhou +1
We study the problem of weakly private information retrieval (PIR) when there is heterogeneity in servers' trustworthiness under the maximal leakage (Max-L) metric and mutual infor…
Federated Linear Bandits with Finite Adversarial Actions
Li Fan, Ruida Zhou, Chao Tian +1
We study a federated linear bandits model, where clients communicate with a central server to solve a linear contextual bandits problem with finite adversarial action sets that…