22 citations · 45 across the 26 of their papers we have counts for
28 papers
Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards
Qirun Zeng, Manhin Poon, Xiangxiang Dai +2
Adversarial attacks on bandits aim to mislead a learner toward a target arm while keeping the attack cost small. Existing attacks typically achieve this by suppressing non-target a…
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…
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…
Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation
Xutong Liu, Baran Atalar, Xiangxiang Dai +5
Large Language Models (LLMs) are revolutionizing how users interact with information systems, yet their high inference cost poses serious scalability and sustainability challenges.…
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…
A Unified Online-Offline Framework for Co-Branding Campaign Recommendations
Xiangxiang Dai, Xiaowei Sun, Jinhang Zuo +2
Co-branding has become a vital strategy for businesses aiming to expand market reach within recommendation systems. However, identifying effective cross-industry partnerships remai…
Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
Qirun Zeng, Eric He, Richard Hoffmann +2
Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting the…
Fusing Reward and Dueling Feedback in Stochastic Bandits
Xuchuang Wang, Qirun Zeng, Jinhang Zuo +4
This paper investigates the fusion of absolute (reward) and relative (dueling) feedback in stochastic bandits, where both feedback types are gathered in each decision round. We der…
Tin-Tin: Towards Tiny Learning on Tiny Devices with Integer-based Neural Network Training
Yi Hu, Jinhang Zuo, Eddie Zhang +2
Recent advancements in machine learning (ML) have enabled its deployment on resource-constrained edge devices, fostering innovative applications such as intelligent environmental s…
Heterogeneous Multi-Agent Bandits with Parsimonious Hints
Amirmahdi Mirfakhar, Xuchuang Wang, Jinhang Zuo +2
We study a hinted heterogeneous multi-agent multi-armed bandits problem (HMA2B), where agents can query low-cost observations (hints) in addition to pulling arms. In this framework…
Offline Learning for Combinatorial Multi-armed Bandits
Xutong Liu, Xiangxiang Dai, Jinhang Zuo +4
The combinatorial multi-armed bandit (CMAB) is a fundamental sequential decision-making framework, extensively studied over the past decade. However, existing work primarily focuse…
Multi-Agent Stochastic Bandits Robust to Adversarial Corruptions
Fatemeh Ghaffari, Xuchuang Wang, Jinhang Zuo +1
We study the problem of multi-agent multi-armed bandits with adversarial corruption in a heterogeneous setting, where each agent accesses a subset of arms. The adversary can corrup…
Stochastic Bandits Robust to Adversarial Attacks
Xuchuang Wang, Jinhang Zuo, Xutong Liu +2
This paper investigates stochastic multi-armed bandit algorithms that are robust to adversarial attacks, where an attacker can first observe the learner's action and {then} alter t…
Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond
Xutong Liu, Siwei Wang, Jinhang Zuo +7
We introduce a novel framework of combinatorial multi-armed bandits (CMAB) with multivariant and probabilistically triggering arms (CMAB-MT), where the outcome of each arm is a …
Quickest Change Detection with Confusing Change
Yu-Zhen Janice Chen, Jinhang Zuo, Venugopal V. Veeravalli +1
In the problem of quickest change detection (QCD), a change occurs at some unknown time in the distribution of a sequence of independent observations. This work studies a QCD probl…
CoRAST: Towards Foundation Model-Powered Correlated Data Analysis in Resource-Constrained CPS and IoT
Yi Hu, Jinhang Zuo, Alanis Zhao +2
Foundation models (FMs) emerge as a promising solution to harness distributed and diverse environmental data by leveraging prior knowledge to understand the complicated temporal an…
Adversarial Attacks on Cooperative Multi-agent Bandits
Jinhang Zuo, Zhiyao Zhang, Xuchuang Wang +5
Cooperative multi-agent multi-armed bandits (CMA2B) consider the collaborative efforts of multiple agents in a shared multi-armed bandit game. We study latent vulnerabilities expos…
Intelligent Communication Planning for Constrained Environmental IoT Sensing with Reinforcement Learning
Yi Hu, Jinhang Zuo, Bob Iannucci +1
Internet of Things (IoT) technologies have enabled numerous data-driven mobile applications and have the potential to significantly improve environmental monitoring and hazard warn…
Adversarial Attacks on Online Learning to Rank with Click Feedback
Jinhang Zuo, Zhiyao Zhang, Zhiyong Wang +3
Online learning to rank (OLTR) is a sequential decision-making problem where a learning agent selects an ordered list of items and receives feedback through user clicks. Although p…
The Online Pause and Resume Problem: Optimal Algorithms and An Application to Carbon-Aware Load Shifting
Adam Lechowicz, Nicolas Christianson, Jinhang Zuo +4
We introduce and study the online pause and resume problem. In this problem, a player attempts to find the lowest (alternatively, highest) prices in a sequence of fixed length…
Contextual Combinatorial Bandits with Probabilistically Triggered Arms
Xutong Liu, Jinhang Zuo, Siwei Wang +4
We study contextual combinatorial bandits with probabilistically triggered arms (CMAB-T) under a variety of smoothness conditions that capture a wide range of applications, suc…
Hierarchical Conversational Preference Elicitation with Bandit Feedback
Jinhang Zuo, Songwen Hu, Tong Yu +3
The recent advances of conversational recommendations provide a promising way to efficiently elicit users' preferences via conversational interactions. To achieve this, the recomme…
Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms
Xutong Liu, Jinhang Zuo, Siwei Wang +3
In this paper, we study the combinatorial semi-bandits (CMAB) and focus on reducing the dependency of the batch-size in the regret bound, where is the total number of arms…
Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
Xutong Liu, Jinhang Zuo, Xiaowei Chen +2
Multi-layered network exploration (MuLaNE) problem is an important problem abstracted from many applications. In MuLaNE, there are multiple network layers where each node has an im…