Searcharxiv⌕ Search

arXiv subjects

Maoli Liu

Publications and source records attributed to Maoli Liu.

8 recordsLinked to original sources

Regret Bounds for Quantum Linear Bandits

We study $d$-dimensional quantum linear bandits with bounded rewards, where the learner selects an action and queries its quantum reward oracle or its inverse in each round. For general action sets, existing algorithms achieve regret $O(d^{3/2}\operatorname{polylog}(T))$ over $T$ rounds. Prior work established a lower bound of $Ω(d\log(1+T/d))$, leaving open whether the $d^{3/2}$ dependence in the upper bound is necessary. We resolve this question by proving a minimax lower bound of $Ω(d^{3/2}\log(1+T/d^{3/2}))$. To prove this result, we construct a family of hard instances in which the reward gap of each action is proportional to its squared distance from the optimal action. We establish a posterior Fisher information bound for adaptive quantum queries with quantum memory, relating the information acquired about the optimal direction to the regret incurred. Viewing each selected action as an estimate of the optimal direction, we use a matrix Cramér--Rao argument to derive a lower bound on expected regret. When the action set is fixed and has size $K$, we propose two phased elimination algorithms, Soft-G-Elim and QG-Elim. We adapt quantum phase estimation to construct SoftQME, a mean estimator with small bias and controlled tails. Soft-G-Elim estimates the mean reward of every surviving action from independent SoftQME outputs on the support of an experimental design. Controlling the bias and fluctuations of these estimates yields regret $O(d\log T\log(dT)\sqrt{\log(KT)})$, reducing the $\log(KT)\log\log(dT)$ factor in the previous regret bound to $\sqrt{\log(KT)}$. QG-Elim further reduces this factor to $\min\{\sqrt{\log(KT)},\sqrt d\}$.

cs.LG↗

Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms

We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB), where the learner queries each arm or action through a quantum reward oracle or its inverse. Prior work gives algorithms over horizon $T$ with regret $O(K\log T)$ for QMAB with $K$ arms and $O(d^2\operatorname{polylog} T)$ for $d$-dimensional QLB. This leaves open the optimal dependence on $K$ and $T$ and whether the dependence on $d$ can be further improved. In this work, we prove the first tight minimax regret bound of $Θ(K\log(1+T/K))$ for QMAB and the first lower bound of $Ω(d\log(1+T/d))$ for finite-action QLB, ruling out regret independent of $T$. Our lower bounds rely on a high-confidence single-arm quantum testing lower bound for distinguishing a fixed reward mean from an interval of alternatives. A bandit-to-testing reduction then lifts it to the QMAB lower bound, while a linear embedding gives the finite-action QLB lower bound. The matching QMAB upper bound is obtained using a tail bound for the Quantum Monte Carlo (QMC) estimator. For finite-action QLB, we propose a phased elimination algorithm that combines a low-bias low-variance quantum mean estimator with a small-support $G$-optimal design through a query allocation matched to the design weights. When the action set has size $\operatorname{poly}(d)$, its regret is nearly linear in $d$ and matches our lower bound up to polylogarithmic factors.

cs.LG↗

Quality-Aware Cross-Model Computation Reuse

An intermediate result computed by one model can be reused by other models to perform their tasks. Existing work mainly focuses on practical execution, leaving a theoretical gap in optimizing reuse decisions. This optimization faces two challenges: quality uncertainty, because the effect of reuse on task quality is uncertain across models, and coupled scheduling, because tasks need to share the cost of preparing reusable results. These challenges compound each other: quality must be learned online, but the shared preparation structure makes scheduling NP-hard even with known quality, breaking the key assumption in existing methods. We formulate cross-model computation reuse as an online decision problem and develop the Quality-Aware Reuse Scheduling (QARS) algorithm to address it. For quality uncertainty, QARS learns task-dependent reuse quality from selected, possibly delayed feedback and uses optimistic estimates to guide decisions. For coupled scheduling, it jointly chooses which results to prepare and which tasks should use them, adapting scheduling accuracy to the remaining quality uncertainty. For the considered problem, our analysis separates learning and optimization error in regret and quantifies the tradeoff between scheduling accuracy and computation. Completing the quality-aware stopping rule yields $\widetilde O(\sqrt{T})$ regret while preserving feasibility. Experiments demonstrate the effectiveness of QARS in optimizing cross-model reuse, reducing the combined cost of computation and quality loss by up to 18.0%, and mean regret by 63.9% over the strongest scheduling baseline.

cs.IR↗

A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responses

Prompt-based offline methods are commonly used to optimize large language model (LLM) responses, but evaluating these responses is computationally intensive and often fails to accommodate diverse response styles. This study introduces a novel online evaluation framework that employs a multi-agent conversational bandit model to select optimal responses while aligning with user preferences dynamically. To tackle challenges such as high-dimensional features, large response sets, adaptive conversational needs, and multi-device access, we propose MACO, Multi-Agent Conversational Online Learning, which comprises two key components: (1) \texttt{MACO-A}: Executed by local agents, it employs an online elimination mechanism to filter out low-quality responses. (2) \texttt{MACO-S}: Executed by the cloud server, it adaptively adjusts selection strategies based on aggregated preference data. An adaptive preference mechanism triggers asynchronous conversations to enhance alignment efficiency. Theoretical analysis demonstrates that MACO achieves near-optimal regret bounds, matching state-of-the-art performance in various degenerate cases. Extensive experiments utilizing Google and OpenAI text embedding models on the real-world datasets with different response styles, combined with Llama and GPT-4o, show that MACO consistently outperforms baseline methods by at least 8.29\% across varying response set sizes and numbers of agents.

cs.HC↗

Learning Best Paths in Quantum Networks

Quantum networks (QNs) transmit delicate quantum information across noisy quantum channels. Crucial applications, like quantum key distribution (QKD) and distributed quantum computation (DQC), rely on efficient quantum information transmission. Learning the best path between a pair of end nodes in a QN is key to enhancing such applications. This paper addresses learning the best path in a QN in the online learning setting. We explore two types of feedback: "link-level" and "path-level". Link-level feedback pertains to QNs with advanced quantum switches that enable link-level benchmarking. Path-level feedback, on the other hand, is associated with basic quantum switches that permit only path-level benchmarking. We introduce two online learning algorithms, BeQuP-Link and BeQuP-Path, to identify the best path using link-level and path-level feedback, respectively. To learn the best path, BeQuP-Link benchmarks the critical links dynamically, while BeQuP-Path relies on a subroutine, transferring path-level observations to estimate link-level parameters in a batch manner. We analyze the quantum resource complexity of these algorithms and demonstrate that both can efficiently and, with high probability, determine the best path. Finally, we perform NetSquid-based simulations and validate that both algorithms accurately and efficiently identify the best path.

cs.NI↗

Leveraging the Power of Conversations: Optimal Key Term Selection in Conversational Contextual Bandits

Conversational recommender systems proactively query users with relevant "key terms" and leverage the feedback to elicit users' preferences for personalized recommendations. Conversational contextual bandits, a prevalent approach in this domain, aim to optimize preference learning by balancing exploitation and exploration. However, several limitations hinder their effectiveness in real-world scenarios. First, existing algorithms employ key term selection strategies with insufficient exploration, often failing to thoroughly probe users' preferences and resulting in suboptimal preference estimation. Second, current algorithms typically rely on deterministic rules to initiate conversations, causing unnecessary interactions when preferences are well-understood and missed opportunities when preferences are uncertain. To address these limitations, we propose three novel algorithms: CLiSK, CLiME, and CLiSK-ME. CLiSK introduces smoothed key term contexts to enhance exploration in preference learning, CLiME adaptively initiates conversations based on preference uncertainty, and CLiSK-ME integrates both techniques. We theoretically prove that all three algorithms achieve a tighter regret upper bound of $O(\sqrt{dT\log{T}})$ with respect to the time horizon $T$, improving upon existing methods. Additionally, we provide a matching lower bound $Ω(\sqrt{dT})$ for conversational bandits, demonstrating that our algorithms are nearly minimax optimal. Extensive evaluations on both synthetic and real-world datasets show that our approaches achieve at least a 14.6% improvement in cumulative regret.

cs.LG↗

Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts

The contextual multi-armed bandit (MAB) problem is crucial in sequential decision-making. A line of research, known as online clustering of bandits, extends contextual MAB by grouping similar users into clusters, utilizing shared features to improve learning efficiency. However, existing algorithms, which rely on the upper confidence bound (UCB) strategy, struggle to gather adequate statistical information to accurately identify unknown user clusters. As a result, their theoretical analyses require several strong assumptions about the "diversity" of contexts generated by the environment, leading to impractical settings, complicated analyses, and poor practical performance. Removing these assumptions has been a long-standing open problem in the clustering of bandits literature. In this paper, we provide two solutions to this open problem. First, following the i.i.d. context generation setting in existing studies, we propose two novel algorithms, UniCLUB and PhaseUniCLUB, which incorporate enhanced exploration mechanisms to accelerate cluster identification. Remarkably, our algorithms require substantially weaker assumptions while achieving regret bounds comparable to prior work. Second, inspired by the smoothed analysis framework, we propose a more practical setting that eliminates the requirement for i.i.d. context generation used in previous studies, thus enhancing the performance of existing algorithms for online clustering of bandits. Our technique can be applied to both graph-based and set-based clustering of bandits frameworks. Extensive evaluations on both synthetic and real-world datasets demonstrate that our proposed algorithms consistently outperform existing approaches.

cs.LG↗

FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clients

Conversational recommender systems have emerged as a potent solution for efficiently eliciting user preferences. These systems interactively present queries associated with "key terms" to users and leverage user feedback to estimate user preferences more efficiently. Nonetheless, most existing algorithms adopt a centralized approach. In this paper, we introduce FedConPE, a phase elimination-based federated conversational bandit algorithm, where $M$ agents collaboratively solve a global contextual linear bandit problem with the help of a central server while ensuring secure data management. To effectively coordinate all the clients and aggregate their collected data, FedConPE uses an adaptive approach to construct key terms that minimize uncertainty across all dimensions in the feature space. Furthermore, compared with existing federated linear bandit algorithms, FedConPE offers improved computational and communication efficiency as well as enhanced privacy protections. Our theoretical analysis shows that FedConPE is minimax near-optimal in terms of cumulative regret. We also establish upper bounds for communication costs and conversation frequency. Comprehensive evaluations demonstrate that FedConPE outperforms existing conversational bandit algorithms while using fewer conversations.

cs.LG↗