21 citations · 27 across the 16 of their papers we have counts for
18 papers
Provable Transformer Context Compression for In-Context Reinforcement Learning
Yajie Zhao, Yingjun Mo, Zhiyong Wang +3
Transformers can perform in-context reinforcement learning without parameter updates. However, existing theoretical constructions often require context sizes that grow with the num…
From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning
Yingjun Mo, Yajie Zhao, Fang Kong
Transformers can implement reinforcement-learning algorithms in context, yet how off-policy control emerges within Transformers remains poorly understood. We study Q-learning, a fo…
A Unified Algorithmic Framework for Hybrid Reinforcement Learning in Tabular MDPs with Shifted Transition Dynamics
Zheshun Wu, Renjie Zheng, Jinhang Zuo +2
This paper investigates a hybrid reinforcement learning setting in tabular Markov Decision Processes (MDPs), where an agent aims to learn an optimal policy by combining online inte…
Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift
Bochao Li, Yao Fu, Wei Chen +1
Offline-to-online learning aims to improve online decision-making by leveraging offline logged data. A central challenge in this setting is the distribution shift between offline a…
A Regret Perspective on Online Multiple Testing
Qingyang Hao, Kongchang Zhou, Fang Kong +1
Online Multiple Testing (OMT), a fundamental pillar of sequential statistical inference, traditionally evaluates the False Discovery Rate (FDR) and statistical power in isolation,…
Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback
Qirun Zeng, Xuchuang Wang, Jiayi Shen +3
We study fixed-confidence best arm identification in generalized linear bandits under a hybrid feedback model: at each round, the learner may query either (i) absolute reward feedb…
Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms
Kongchang Zhou, Tingyu Zhang, Wei Chen +1
The problem of combinatorial multi-armed bandits with probabilistically triggered arms (CMAB-T) has been extensively studied. Prior work primarily focuses on either the online sett…
Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution
Manhin Poon, XiangXiang Dai, Xutong Liu +3
Large language models (LLMs) exhibit diverse response behaviors, costs, and strengths, making it challenging to select the most suitable LLM for a given user query. We study the pr…
Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits
Yu Xia, Fang Kong, Tong Yu +4
Web-based applications such as chatbots, search engines and news recommendations continue to grow in scale and complexity with the recent surge in the adoption of LLMs. Online mode…
Improved Bandits in Many-to-one Matching Markets with Incentive Compatibility
Fang Kong, Shuai Li
Two-sided matching markets have been widely studied in the literature due to their rich applications. Since participants are usually uncertain about their preferences, online algor…
Player-optimal Stable Regret for Bandit Learning in Matching Markets
Fang Kong, Shuai Li
The problem of matching markets has been studied for a long time in the literature due to its wide range of applications. Finding a stable matching is a common equilibrium objectiv…
Online Influence Maximization under Decreasing Cascade Model
Fang Kong, Jize Xie, Baoxiang Wang +2
We study online influence maximization (OIM) under a new model of decreasing cascade (DC). This model is a generalization of the independent cascade (IC) model by considering the c…
Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm
Fang Kong, Canzhe Zhao, Shuai Li
The linear bandit problem has been studied for many years in both stochastic and adversarial settings. Designing an algorithm that can optimize the environment without knowing the…
Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization
Fang Kong, Xiangcheng Zhang, Baoxiang Wang +1
Learning Markov decision processes (MDP) in an adversarial environment has been a challenging problem. The problem becomes even more challenging with function approximation, since…
Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback
Fang Kong, Yichi Zhou, Shuai Li
The problem of online learning with graph feedback has been extensively studied in the literature due to its generality and potential to model various learning tasks. Existing work…
Thompson Sampling for Bandit Learning in Matching Markets
Fang Kong, Junming Yin, Shuai Li
The problem of two-sided matching markets has a wide range of real-world applications and has been extensively studied in the literature. A line of recent works have focused on the…
The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle
Fang Kong, Yueran Yang, Wei Chen +1
Thompson sampling (TS) has attracted a lot of interest in the bandit area. It was introduced in the 1930s but has not been theoretically proven until recent years. All of its analy…
Online Influence Maximization under Linear Threshold Model
Shuai Li, Fang Kong, Kejie Tang +2
Online influence maximization (OIM) is a popular problem in social networks to learn influence propagation model parameters and maximize the influence spread at the same time. Most…