Search Results for author:
Found 49 papers, 9 papers with code
Learning Best Paths in Quantum Networks
We introduce two online learning algorithms, BeQuP-Link and BeQuP-Path, to identify the best path using link-level and path-level feedback, respectively.
Federated In-Context Learning: Iterative Refinement for Improved Answer Quality
For question-answering (QA) tasks, in-context learning (ICL) enables language models to generate responses without modifying their parameters by leveraging examples provided in the input.
Offline Clustering of Linear Bandits: Unlocking the Power of Clusters in Data-Limited Environments
The key challenge in Off-ClusBand arises from data insufficiency for users: unlike the online case, 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.
Online Clustering of Dueling Bandits
In applications involving a large number of users, the performance of contextual MAB can be significantly improved by facilitating collaboration among multiple users.
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.
Multi-Agent Conversational Online Learning for Adaptive LLM Response Identification
The remarkable generative capability of large language models (LLMs) has sparked a growing interest in automatically generating responses for different applications.
Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts
context generation used in previous studies, thus enhancing the performance of existing algorithms for online clustering of bandits.
Unifying KV Cache Compression for Large Language Models with LeanKV
Large language models (LLMs) exhibit exceptional performance but incur significant serving costs due to their substantial memory requirements, with the key-value (KV) cache being a primary bottleneck.
Combinatorial Logistic Bandits
Under the 1-norm triggering probability modulated (TPM) smoothness condition, CLogUCB achieves a regret bound of $\tilde{O}(d\sqrt{\kappa KT})$, where $\tilde{O}$ ignores logarithmic factors, $d$ is the dimension of the feature vector, $\kappa$ represents the nonlinearity of the logistic model, and $K$ is the maximum number of base arms a super arm can trigger.
Stochastic Bandits Robust to Adversarial Attacks
For both cases, we devise two types of algorithms with regret bounds having additive or multiplicative $C$ dependence terms.
Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds
Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning inside the learned model is perhaps the most standard and simplest Model-based Reinforcement Learning (RL) framework.
AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics
The rapid evolution of multimedia and computer vision technologies requires adaptive visual model deployment strategies to effectively handle diverse tasks and varying environments.
Merit-based Fair Combinatorial Semi-Bandit with Unrestricted Feedback Delays
We study the stochastic combinatorial semi-bandit problem with unrestricted feedback delays under merit-based fairness constraints.
Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond
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 $d$-dimensional multivariant random variable and the feedback follows a general arm triggering process.
Cost-Effective Online Multi-LLM Selection with Versatile Reward Models
The NP-hard integer linear programming problem for selecting multiple LLMs with trade-off dilemmas is addressed by: i) decomposing the integer problem into a relaxed form by the local server, ii) utilizing a discretization rounding scheme that provides optimal LLM combinations by the scheduling cloud, and iii) continual online updates based on feedback.
FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clients
These systems interactively present queries associated with "key terms" to users and leverage user feedback to estimate user preferences more efficiently.
Variance-Dependent Regret Bounds for Non-stationary Linear Bandits
We investigate the non-stationary stochastic linear bandit problem where the reward distribution evolves each round.
Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users
We study the problem of federated contextual combinatorial cascading bandits, where $|\mathcal{U}|$ agents collaborate under the coordination of a central server to provide tailored recommendations to the $|\mathcal{U}|$ corresponding users.
Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codes
In Federated Learning (FL) paradigm, a parameter server (PS) concurrently communicates with distributed participating clients for model collection, update aggregation, and model distribution over multiple rounds, without touching private data owned by individual clients.
Adversarial Attacks on Cooperative Multi-agent Bandits
Cooperative multi-agent multi-armed bandits (CMA2B) consider the collaborative efforts of multiple agents in a shared multi-armed bandit game.
Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs
Prior algorithms in both paradigms achieve the optimal group regret.
A Survey of Federated Evaluation in Federated Learning
In traditional machine learning, it is trivial to conduct model evaluation since all data samples are managed centrally by a server.
Contextual Combinatorial Bandits with Probabilistically Triggered Arms
We study contextual combinatorial bandits with probabilistically triggered arms (C$^2$MAB-T) under a variety of smoothness conditions that capture a wide range of applications, such as contextual cascading bandits and contextual influence maximization bandits.
Efficient Explorative Key-term Selection Strategies for Conversational Contextual Bandits
To tackle these issues, we first propose ``ConLinUCB", a general framework for conversational bandits with better information incorporation, combining arm-level and key-term-level feedback to estimate user preference in one step at each time.
On-Demand Communication for Asynchronous Multi-Agent Bandits
We propose ODC, an on-demand communication protocol that tailors the communication of each pair of agents based on their empirical pull times.
Interactive Log Parsing via Light-weight User Feedback
Template mining is one of the foundational tasks to support log analysis, which supports the diagnosis and troubleshooting of large scale Web applications.
Online Search with Predictions: Pareto-optimal Algorithm and its Applications in Energy Markets
This paper develops learning-augmented algorithms for energy trading in volatile electricity markets.
Federated Online Clustering of Bandits
Contextual multi-armed bandit (MAB) is an important sequential decision-making problem in recommendation systems.
Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms
Under this new condition, we propose a BCUCB-T algorithm with variance-aware confidence intervals and conduct regret analysis which reduces the $O(K)$ factor to $O(\log K)$ or $O(\log^2 K)$ in the regret bound, significantly improving the regret bounds for the above applications.
Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms
When the "per-load" reward follows a Gaussian distribution, we prove a sample complexity lower bound of learning the capacity from load-dependent rewards and also a regret lower bound of this new MP-MAB problem.
LPC-AD: Fast and Accurate Multivariate Time Series Anomaly Detection via Latent Predictive Coding
LPC-AD is motivated by the ever-increasing needs for fast and accurate MTS anomaly detection methods to support fast troubleshooting in cloud computing, micro-service systems, etc.
Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms & Applications
The reward from a shareable arm is equal to the "per-load" reward multiplied by the minimum between the number of players pulling the arm and the arm's maximal shareable resources.
Decentralized Task Offloading in Edge Computing: A Multi-User Multi-Armed Bandit Approach
Mobile edge computing facilitates users to offload computation tasks to edge servers for meeting their stringent delay requirements.
Decentralized Stochastic Proximal Gradient Descent with Variance Reduction over Time-varying Networks
By transforming our decentralized algorithm into a centralized inexact proximal gradient algorithm with variance reduction, and controlling the bounds of error sequences, we prove that DPSVRG converges at the rate of $O(1/T)$ for general convex objectives plus a non-smooth term with $T$ as the number of iterations, while DSPG converges at the rate $O(\frac{1}{\sqrt{T}})$.
Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback
This paper studies a cooperative multi-armed bandit problem with $M$ agents cooperating together to solve the same instance of a $K$-armed stochastic bandit problem with the goal of maximizing the cumulative reward of agents.
Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
For the online learning setting, neither the network structure nor the node weights are known initially.
Adversarial Bandits with Corruptions: Regret Lower Bound and No-regret Algorithm
We characterize the regret of ExpRb as a function of the corruption budget and show that for the case of a known corruption budget, the regret of ExpRb is tight.
Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits
Compared to existing algorithms, our result eliminates the exponential factor (in $M, N$) in the regret upper bound, due to a novel exploitation of the sparsity in transitions in general restless bandit problems.
Online Competitive Influence Maximization
In this paper, we introduce a new Online Competitive Influence Maximization (OCIM) problem, where two competing items (e. g., products, news stories) propagate in the same network and influence probabilities on edges are unknown.
Walking with Perception: Efficient Random Walk Sampling via Common Neighbor Awareness
Random walk is widely applied to sample large-scale graphs due to its simplicity of implementation and solid theoretical foundations of bias analysis.
Combining Offline Causal Inference and Online Bandit Learning for Data Driven Decision
A typical alternative is offline causal inference, which analyzes logged data alone to make decisions.
Conversational Contextual Bandit: Algorithm and Application
Here, a key-term can relate to a subset of arms, for example, a category of articles in news recommendation.
Community Exploration: From Offline Optimization to Online Learning
We introduce the community exploration problem that has many real-world applications such as online advertising.
Graphlet Count Estimation via Convolutional Neural Networks
The number of each graphlet, called graphlet count, is a signature which characterizes the local network structure of a given graph.
Beyond the Click-Through Rate: Web Link Selection with Multi-level Feedback
The web link selection problem is to select a small subset of web links from a large web link pool, and to place the selected links on a web page that can only accommodate a limited number of links, e. g., advertisements, recommendations, or news feeds.
Multi-level Feedback Web Links Selection Problem: Learning and Optimization
To our best knowledge, we are the first to model the links selection problem as a constrained multi-armed bandit problem and design an effective links selection algorithm by learning the links' multi-level structure with provable \emph{sub-linear} regret and violation bounds.
Monet: A User-oriented Behavior-based Malware Variants Detection System for Android
We present the design and implementation of MONET, which has a client and a backend server module.
Cryptography and Security
DroidAnalytics: A Signature Based Analytic System to Collect, Extract, Analyze and Associate Android Malware
In this paper, we present the design and implementation of DroidAnalytics, a signature based analytic system to automatically collect, manage, analyze and extract android malware.
Cryptography and Security
Online Robust Subspace Tracking from Partial Information
This paper presents GRASTA (Grassmannian Robust Adaptive Subspace Tracking Algorithm), an efficient and robust online algorithm for tracking subspaces from highly incomplete information.
