arXiv subjects

Xutong Liu

Publications and source records attributed to Xutong Liu.

At least 19 recordsLinked to original sources

arXiv2026

FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching

Federated learning (FL) is often subject to aggregation variance if clients do not consistently participate in training rounds. While reusing stale model updates from inactive clients is a common technique to reduce this variance, we find that with skewed client participation, the resulting update staleness can become severe enough to destabilize training. To remedy this, we propose FedSteer, a novel method that constructs a gradient subspace from a cache of recent client gradients to serve as a low-dimensional representation of the current optimization landscape. FedSteer projects an active client's true gradient onto this subspace to find a set of optimal coordinates. For an inactive client, FedSteer reuses these coordinates with the now-evolved subspace drifted by other active clients. This process effectively "steers" outdated gradients toward the current global objective. This is complemented by a selective caching strategy that identifies a representative client subset to form the subspace, reducing server memory. Experiments demonstrate that FedSteer significantly outperforms baselines, preventing performance collapse in challenging scenarios while delivering accuracy gains of over 7% in others.

cs.LG↗

arXiv2026

Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback

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 feedback from a single arm or (ii) relative (dueling) feedback from an arm pair, both governed by generalized linear models. We introduce a likelihood-ratio--based confidence sequence that unifies heterogeneous generalized linear observations and yields an explicit ellipsoidal confidence set under a self-concordance assumption. Building on this confidence set, we propose a hybrid Track-and-Stop algorithm that adaptively allocates queries by tracking a minimax-optimal design over a joint action space of arms and pairs. We establish $δ$-correctness and provide high-probability upper bounds on the stopping time. We further extend the framework to a cost-aware setting that accounts for heterogeneous acquisition costs across feedback modalities. Empirical experiments demonstrate that the proposed algorithms significantly improve sample efficiency over baseline methods.

cs.AI↗

arXiv2026

Scaling Federated Linear Contextual Bandits via Sketching

In federated contextual linear bandits, high data dimensionality incurs prohibitive computation and communication costs: local agents perform $O(d^3)$-time determinant computation and upload $O(d^2)$ parameters, making existing algorithms unscalable, where $d$ is the dimension of data. To relieve these scaling bottlenecks, this paper proposes Federated Sketch Contextual Linear Bandits (FSCLB). On the computation side, FSCLB uses SVD to indirectly obtain the determinant required for communication, eliminating the prohibitive cost of direct determinant calculation and cutting complexity from $O(d^3)$ to $O(l^2d)$ per round, where $l< d$ is the sketch size. On the communication side, FSCLB introduces a double-sketch strategy that reduces both upload and download costs from $O(d^2)$ to $O(ld)$. Naively involving sketch update into federated contextual linear bandits can destroy the local increment and invalidate the asynchronous communication condition; FSCLB solves this by replacing the covariance matrix with the sketch matrix when deciding whether to communicate. Theoretically, FSCLB achieves a regret bound of $\widetilde{O} ((\sqrt{d}+\sqrt{M\varepsilon_l})\sqrt{lT})$, where $\varepsilon_l$ is the upper bounded by the spectral tail of the covariance matrix; when $l$ exceeds the rank of the covariance matrix, the bound simplifies to $\widetilde{O}(\sqrt{ldT})$, matching the optimal no-sketch regret. Experiments on both synthetic and real-world datasets show that FSCLB significantly reduces computational and communication costs by over 90 \% while sacrificing only a negligible amount of cumulative reward.

cs.LG↗

arXiv2026

Unlearning Offline Stochastic Multi-Armed Bandits

Machine unlearning aims to unlearn data points from a learned model, offering a principled way to process data-deletion requests and mitigate privacy risks without full retraining. Prior work has mainly studied unsupervised / supervised machine unlearning, leaving unlearning for sequential decision-making systems far less understood. We initiate the first study of a foundational sequential decision-making problem: offline stochastic multi-armed bandits (MAB). We formalize the privacy constraint for offline MAB and measure utility by the post-unlearning decision quality. We conduct a systematic study of both single- and multi-source unlearning scenarios under two data-generation models, the fixed-sample model and the distribution model. For these settings, our algorithmic design is built on two canonical base algorithms: Gaussian mechanism and rollback, and we propose adaptive algorithms that switch between them according to the data regime and privacy constraint. We further introduce a mixing procedure that elucidates the rationale behind these baselines. We provide performance guarantees across the above settings and establish lower bounds under both dataset models. Experiments validate the predicted tradeoffs and demonstrate the effectiveness of the proposed methods.

cs.LG↗

arXiv2026

Continuous Semantic Caching for Low-Cost LLM Serving

As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries has become a vital strategy for reducing inference costs and latency. Existing caching frameworks have proposed to decide which query responses to cache by assuming a finite, known universe of discrete queries and learning their serving costs and arrival probabilities. As LLMs' pool of users and queries expands, however, such an assumption becomes increasingly untenable: real-world LLM queries reside in an infinite, continuous embedding space. In this paper, we establish the first rigorous theoretical framework for semantic LLM response caching in continuous query space under uncertainty. To bridge the gap between discrete optimization and continuous representation spaces, we introduce dynamic $ε$-net discretization coupled with Kernel Ridge Regression. This design enables the system to formally quantify estimation uncertainty and generalize partial feedback on LLM query costs across continuous semantic query neighborhoods. We develop both offline learning and online adaptive algorithms optimized to reduce switching costs incurred by changing the cached responses. We prove that our online algorithm achieves a sublinear regret bound against an optimal continuous oracle, which reduces to existing bounds for discrete query models. Extensive empirical evaluations demonstrate that our framework approximates the continuous optimal cache well while also reducing computational and switching overhead compared to existing methods.

cs.LG↗

arXiv2026

Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing

Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, real-world safety is a full-lifecycle problem: static defenses degrade against evolving jailbreak behaviors, and fixed weights cannot adapt to pluralistic, time-varying safety norms. This motivates inference-time governance that steers behavior without costly retraining. To address this, we introduce the Consensus Clustering LinUCB Bandit (CCLUB), a unified framework for adaptive social alignment via system-prompt routing. CCLUB employs a conservative consensus clustering mechanism: it pools data only within the intersection of utility and safety similarity graphs, effectively preventing unsafe generalization across semantically proximal but risk-divergent contexts. Our theoretical analysis yields a sublinear regret guarantee, demonstrating near-optimal performance of CCLUB. Extensive experiments validate that CCLUB outperforms strong baselines, achieving a 10.98% improvement in cumulative reward and a 14.42% reduction in the average suboptimality gap.

cs.LG↗

arXiv2026

Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation

Large Language Models (LLMs) are revolutionizing how users interact with information systems, yet their high inference cost poses serious scalability and sustainability challenges. Caching inference responses, allowing them to be retrieved without another forward pass through the LLM, has emerged as one possible solution. Traditional exact-match caching, however, overlooks the semantic similarity between queries, leading to unnecessary recomputation. Semantic caching addresses this by retrieving responses based on semantic similarity, but introduces a fundamentally different cache eviction problem: one must account for mismatch costs between incoming queries and cached responses. Moreover, key system parameters, such as query arrival probabilities and serving costs, are often unknown and must be learned over time. Existing semantic caching methods are largely ad-hoc, lacking theoretical foundations and unable to adapt to real-world uncertainty. In this paper, we present a principled, learning-based framework for semantic cache eviction under unknown query and cost distributions. We formulate both offline optimization and online learning variants of the problem, and develop provably efficient algorithms with state-of-the-art guarantees. We also evaluate our framework on a synthetic dataset, showing that our proposed algorithms perform matching or superior performance compared with baselines.

cs.LG↗

arXiv2026

Faster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference

Sparse Mixture of Experts (SMoE) has become a preferred architecture for scaling Transformer capacity without increasing computational cost, as it activates only a small subset of experts for each input. However, deploying such an approach for \textit{online inference} remains challenging due to the large size of a full SMoE model and the complexity of expert routing, especially in resource-constrained edge networks. Moreover, during the online inference, task information is often unavailable, making the task-level routing error-prone. In this work, we propose a novel tree-structured adaptive neural bandit router, \texttt{Tanbr}, to enable efficient and reliable online MoE inference. Instead of relying on explicit task tags, \texttt{Tanbr} estimates the task distribution over time from historical data and uses it to guide task-aware expert merging within a given pre-trained MoE. To handle the large continuous space of merging weights, \texttt{Tanbr} employs a binary tree to progressively partition the space and generate finer candidate weights. It then applies a neural bandit to learn the non-linear mapping from merging weight to model performance and decides optimal expert merging. We prove that \texttt{Tanbr} achieves a sublinear regret bound of {\small $\mathcal{O}(\sqrt{T} \log(T))$} over {\small $T$} rounds, despite operating over a continuous decision space, matching regret bounds compared to existing methods. Extensive experiments show that \texttt{Tanbr} reduces inference latency by at least {\small $45\%$} and memory usage by up to {\small $25\%$}, while maintaining a high accuracy compared to many state-of-the-art methods.

cs.LG↗

arXiv2025

Near-Optimal Regret for Efficient Stochastic Combinatorial Semi-Bandits

The combinatorial multi-armed bandit (CMAB) is a cornerstone of sequential decision-making framework, dominated by two algorithmic families: UCB-based and adversarial methods such as follow the regularized leader (FTRL) and online mirror descent (OMD). However, prominent UCB-based approaches like CUCB suffer from additional regret factor $\log T$ that is detrimental over long horizons, while adversarial methods such as EXP3.M and HYBRID impose significant computational overhead. To resolve this trade-off, we introduce the Combinatorial Minimax Optimal Strategy in the Stochastic setting (CMOSS). CMOSS is a computationally efficient algorithm that achieves an instance-independent regret of $O\big( (\log k)\sqrt{kmT}\big )$ when $k\leq \frac{m}{2}$ and $O\big((m-k)\sqrt{\log k\log(m-k)T}\big )$ when $k>\frac{m}{2}$ under semi-bandit feedback, where $m$ is the number of arms and $k$ is the maximum cardinality of a feasible action. Crucially, this result eliminates the dependency on $\log T$ and matches the established lower bounds of $Ω\big(\sqrt{kmT}\big)$ when $k\leq \frac{m}{2}$ and $Ω\big((m-k)\sqrt{\log (\frac{m}{m-k}) T}\big)$ when $k>\frac{m}{2}$ up to logarithmic terms of $k$ and $m$. We then extend our analysis to show that CMOSS is also applicable to cascading feedback. Experiments on synthetic and real-world datasets validate that CMOSS consistently outperforms benchmark algorithms in both regret and runtime efficiency.

cs.LG↗

arXiv2025

Online Learning to Rank under Corruption: A Robust Cascading Bandits Approach

Online learning to rank (OLTR) studies how to recommend a short ranked list of items from a large pool and improves future rankings based on user clicks. This setting is commonly modeled as cascading bandits, where the objective is to maximize the likelihood that the user clicks on at least one of the presented items across as many timesteps as possible. However, such systems are vulnerable to click fraud and other manipulations (i.e., corruption), where bots or paid click farms inject corrupted feedback that misleads the learning process and degrades user experience. In this paper, we propose MSUCB, a robust algorithm that incorporates a novel mean-of-medians estimator, which to our knowledge is applied to bandits with corruption setting for the first time. This estimator behaves like a standard mean in the absence of corruption, so no cost is paid for robustness. Under corruption, the median step filters out outliers and corrupted samples, keeping the estimate close to its true value. Updating this estimate at every round further accelerates empirical convergence in experiments. Hence, MSUCB achieves optimal logarithmic regret in the absence of corruption and degrades gracefully under corruptions, with regret increasing only by an additive term tied to the total corruption. Comprehensive and extensive experiments on real-world datasets further demonstrate that our approach consistently outperforms prior methods while maintaining strong robustness. In particular, it achieves a $97.35\%$ and a $91.60\%$ regret improvement over two state-of-the-art methods.

cs.LG↗

arXiv2025

Offline Clustering of Preference Learning with Active-data Augmentation

Preference learning from pairwise feedback is a widely adopted framework in applications such as reinforcement learning with human feedback and recommendations. In many practical settings, however, user interactions are limited or costly, making offline preference learning necessary. Moreover, real-world preference learning often involves users with different preferences. For example, annotators from different backgrounds may rank the same responses differently. This setting presents two central challenges: (1) identifying similarity across users to effectively aggregate data, especially under scenarios where offline data is imbalanced across dimensions, and (2) handling the imbalanced offline data where some preference dimensions are underrepresented. To address these challenges, we study the Offline Clustering of Preference Learning problem, where the learner has access to fixed datasets from multiple users with potentially different preferences and aims to maximize utility for a test user. To tackle the first challenge, we first propose Off-C$^2$PL for the pure offline setting, where the learner relies solely on offline data. Our theoretical analysis provides a suboptimality bound that explicitly captures the tradeoff between sample noise and bias. To address the second challenge of inbalanced data, we extend our framework to the setting with active-data augmentation where the learner is allowed to select a limited number of additional active-data for the test user based on the cluster structure learned by Off-C$^2$PL. In this setting, our second algorithm, A$^2$-Off-C$^2$PL, actively selects samples that target the least-informative dimensions of the test user's preference. We prove that these actively collected samples contribute more effectively than offline ones. Finally, we validate our theoretical results through simulations on synthetic and real-world datasets.

cs.LG↗

arXiv2025

Offline Clustering of Linear Bandits: The Power of Clusters under Limited Data

Contextual multi-armed bandit is a fundamental learning framework for making a sequence of decisions, e.g., advertising recommendations for a sequence of arriving users. Recent works have shown that clustering these users based on the similarity of their learned preferences can accelerate the learning. However, prior work has primarily focused on the online setting, which requires continually collecting user data, ignoring the offline data widely available in many applications. To tackle these limitations, we study the offline clustering of bandits (Off-ClusBand) problem, which studies how to use the offline dataset to learn cluster properties and improve decision-making. The key challenge in Off-ClusBand arises from data insufficiency for users: unlike the online case where we continually learn from online data, in the offline case, we have a fixed, limited dataset to work from and thus must determine whether we have enough data to confidently cluster users together. To address this challenge, we propose two algorithms: Off-C2LUB, which we show analytically and experimentally outperforms existing methods under limited offline user data, and Off-CLUB, which may incur bias when data is sparse but performs well and nearly matches the lower bound when data is sufficient. We experimentally validate these results on both real and synthetic datasets.

cs.LG↗

arXiv2025

HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization

Low-Rank Adaptation (LoRA) has emerged as a widely used technique for adapting large language models (LLMs) to new domains, due to its modular design and broad availability on platforms such as HuggingFace. This availability has motivated efforts to reuse existing LoRAs for domain generalization. However, existing methods often rely on explicit task labels or additional training, which are impractical for deployment. Moreover, they typically activate a fixed number of entire LoRA modules, leading to parameter redundancy or insufficiency that degrade performance. In this paper, we propose \texttt{HiLoRA}, a training-free framework that performs adaptive hierarchical routing over LoRA pools. Drawing on structural properties of LoRA, we define rank-one components (ROCs), in which each rank parameter is regarded as an independent unit. For a given input sequence, \texttt{HiLoRA} first adaptively selects a subset of LoRAs and determines their ROC allocation based on Gaussian likelihoods at the sequence level. At the token level, it further refines routing by activating only the most informative ROCs. We further provide theoretical guarantees that \texttt{HiLoRA} selects the most relevant LoRAs with high probability. Extensive experiments show that \texttt{HiLoRA} achieves substantial improvements in domain generalization, with accuracy gains of up to {\small $55\%$} over state-of-the-art baselines, while maintaining comparable inference throughput.

cs.LG↗

arXiv2025

Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution

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 problem of adaptive multi-LLM selection in an online setting, where the learner interacts with users through multi-step query refinement and must choose LLMs sequentially without access to offline datasets or model internals. A key challenge arises from unstructured context evolution: the prompt dynamically changes in response to previous model outputs via a black-box process, which cannot be simulated, modeled, or learned. To address this, we propose the first contextual bandit framework for sequential LLM selection under unstructured prompt dynamics. We formalize a notion of myopic regret and develop a LinUCB-based algorithm that provably achieves sublinear regret without relying on future context prediction. We further introduce budget-aware and positionally-aware (favoring early-stage satisfaction) extensions to accommodate variable query costs and user preferences for early high-quality responses. Our algorithms are theoretically grounded and require no offline fine-tuning or dataset-specific training. Experiments on diverse benchmarks demonstrate that our methods outperform existing LLM routing strategies in both accuracy and cost-efficiency, validating the power of contextual bandits for real-time, adaptive LLM selection.

cs.LG↗

arXiv2025

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↗

arXiv2025

Offline Learning for Combinatorial Multi-armed Bandits

The combinatorial multi-armed bandit (CMAB) is a fundamental sequential decision-making framework, extensively studied over the past decade. However, existing work primarily focuses on the online setting, overlooking the substantial costs of online interactions and the readily available offline datasets. To overcome these limitations, we introduce Off-CMAB, the first offline learning framework for CMAB. Central to our framework is the combinatorial lower confidence bound (CLCB) algorithm, which combines pessimistic reward estimations with combinatorial solvers. To characterize the quality of offline datasets, we propose two novel data coverage conditions and prove that, under these conditions, CLCB achieves a near-optimal suboptimality gap, matching the theoretical lower bound up to a logarithmic factor. We validate Off-CMAB through practical applications, including learning to rank, large language model (LLM) caching, and social influence maximization, showing its ability to handle nonlinear reward functions, general feedback models, and out-of-distribution action samples that excludes optimal or even feasible actions. Extensive experiments on synthetic and real-world datasets further highlight the superior performance of CLCB.

cs.LG↗

arXiv2025

A Unified Online-Offline Framework for Co-Branding Campaign Recommendations

Co-branding has become a vital strategy for businesses aiming to expand market reach within recommendation systems. However, identifying effective cross-industry partnerships remains challenging due to resource imbalances, uncertain brand willingness, and ever-changing market conditions. In this paper, we provide the first systematic study of this problem and propose a unified online-offline framework to enable co-branding recommendations. Our approach begins by constructing a bipartite graph linking ``initiating'' and ``target'' brands to quantify co-branding probabilities and assess market benefits. During the online learning phase, we dynamically update the graph in response to market feedback, while striking a balance between exploring new collaborations for long-term gains and exploiting established partnerships for immediate benefits. To address the high initial co-branding costs, our framework mitigates redundant exploration, thereby enhancing short-term performance while ensuring sustainable strategic growth. In the offline optimization phase, our framework consolidates the interests of multiple sub-brands under the same parent brand to maximize overall returns, avoid excessive investment in single sub-brands, and reduce unnecessary costs associated with over-prioritizing a single sub-brand. We present a theoretical analysis of our approach, establishing a highly nontrivial sublinear regret bound for online learning in the complex co-branding problem, and enhancing the approximation guarantee for the NP-hard offline budget allocation optimization. Experiments on both synthetic and real-world co-branding datasets demonstrate the practical effectiveness of our framework, with at least 12\% improvement.

cs.LG↗

arXiv2025

Combinatorial Logistic Bandits

We introduce a novel framework called combinatorial logistic bandits (CLogB), where in each round, a subset of base arms (called the super arm) is selected, with the outcome of each base arm being binary and its expectation following a logistic parametric model. The feedback is governed by a general arm triggering process. Our study covers CLogB with reward functions satisfying two smoothness conditions, capturing application scenarios such as online content delivery, online learning to rank, and dynamic channel allocation. We first propose a simple yet efficient algorithm, CLogUCB, utilizing a variance-agnostic exploration bonus. Under the 1-norm triggering probability modulated (TPM) smoothness condition, CLogUCB achieves a regret bound of $\tilde{O}(d\sqrt{κKT})$, where $\tilde{O}$ ignores logarithmic factors, $d$ is the dimension of the feature vector, $κ$ represents the nonlinearity of the logistic model, and $K$ is the maximum number of base arms a super arm can trigger. This result improves on prior work by a factor of $\tilde{O}(\sqrtκ)$. We then enhance CLogUCB with a variance-adaptive version, VA-CLogUCB, which attains a regret bound of $\tilde{O}(d\sqrt{KT})$ under the same 1-norm TPM condition, improving another $\tilde{O}(\sqrtκ)$ factor. VA-CLogUCB shows even greater promise under the stronger triggering probability and variance modulated (TPVM) condition, achieving a leading $\tilde{O}(d\sqrt{T})$ regret, thus removing the additional dependency on the action-size $K$. Furthermore, we enhance the computational efficiency of VA-CLogUCB by eliminating the nonconvex optimization process when the context feature map is time-invariant while maintaining the tight $\tilde{O}(d\sqrt{T})$ regret. Finally, experiments on synthetic and real-world datasets demonstrate the superior performance of our algorithms compared to benchmark algorithms.

cs.LG↗