Search Results for author:
Found 38 papers, 4 papers with code
Robust Bayesian Satisficing
In addition, we define a weaker notion of regret called robust satisficing regret, in which our algorithm achieves a sublinear upper bound independent of the amount of distribution shift.
Robust Pareto Set Identification with Contaminated Bandit Feedback
We consider the Pareto set identification (PSI) problem in multi-objective multi-armed bandits (MO-MAB) with contaminated reward observations.
Federated Multi-Armed Bandits Under Byzantine Attacks
We demonstrate Fed-MoM-UCB's effectiveness against the baselines in the presence of Byzantine attacks via experiments.
Safe Linear Leveling Bandits
In this work, we tackle a different critical task through the lens of \textit{linear stochastic bandits}, where the aim is to keep the actions' outcomes close to a target level while respecting a \textit{two-sided} safety constraint, which we call \textit{leveling}.
Contextual Combinatorial Multi-output GP Bandits with Group Constraints
In federated multi-armed bandit problems, maximizing global reward while satisfying minimum privacy requirements to protect clients is the main goal.
ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine
We propose ESCADA, a novel and generic multi-armed bandit (MAB) algorithm tailored for the leveling task, to make safe, personalized, and context-aware dose recommendations.
Vector Optimization with Stochastic Bandit Feedback
We introduce vector optimization problems with stochastic bandit feedback, in which preferences among designs are encoded by a polyhedral ordering cone $C$.
Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processes
We consider a contextual bandit problem with a combinatorial action set and time-varying base arm availability.
Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values
Secondly, such datasets are usually imperfect, additionally cursed with missing values in the attributes of features.
Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning
Understanding human behavior from observed data is critical for transparency and accountability in decision-making.
Contextual Combinatorial Volatile Multi-armed Bandit with Adaptive Discretization
We consider contextual combinatorial volatile multi-armed bandit (CCV-MAB), in which at each round, the learner observes a set of available base arms and their contexts, and then, selects a super arm that contains $K$ base arms in order to maximize its cumulative reward.
Pareto Active Learning with Gaussian Processes and Adaptive Discretization
We consider the problem of optimizing a vector-valued objective function $\boldsymbol{f}$ sampled from a Gaussian Process (GP) whose index set is a well-behaved, compact metric space $({\cal X}, d)$ of designs.
Lexicographic Multiarmed Bandit
The algorithm we propose for the second setting also attains bounded regret for the multiarmed bandit with satisficing objectives.
Thompson Sampling for Combinatorial Network Optimization in Unknown Environments
Influence maximization, adaptive routing, and dynamic spectrum allocation all require choosing the right action from a large set of alternatives.
Exploiting Relevance for Online Decision-Making in High-Dimensions
As our learning model, we consider a structured contextual multi-armed bandit (CMAB) with high-dimensional arm (action) and context (data) sets, where the rewards depend only on a few relevant dimensions of the joint context-arm set, possibly in a non-linear way.
Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairness
Machine Learning (ML) models trained on data from multiple demographic groups can inherit representation disparity (Hashimoto et al., 2018) that may exist in the data: the model may be less favorable to groups contributing less to the training process; this in turn can degrade population retention in these groups over time, and exacerbate representation disparity in the long run.
Analysis of Thompson Sampling for Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms
We analyze the regret of combinatorial Thompson sampling (CTS) for the combinatorial multi-armed bandit with probabilistically triggered arms under the semi-bandit feedback setting.
Multi-objective Contextual Bandit Problem with Similarity Information
Essentially, the contextual Pareto regret is the sum of the distances of the arms chosen by the learner to the context dependent Pareto front.
Combinatorial Multi-Objective Multi-Armed Bandit Problem
In this paper, we introduce the COmbinatorial Multi-Objective Multi-Armed Bandit (COMO-MAB) problem that captures the challenges of combinatorial and multi-objective online learning simultaneously.
Multi-objective Contextual Multi-armed Bandit with a Dominant Objective
In this case, the optimal arm given a context is the one that maximizes the expected reward in the non-dominant objective among all arms that maximize the expected reward in the dominant objective.
Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms: A Case with Bounded Regret
Under the assumption that the arm triggering probabilities (ATPs) are positive for all arms, we prove that a class of upper confidence bound (UCB) policies, named Combinatorial UCB with exploration rate $\kappa$ (CUCB-$\kappa$), and Combinatorial Thompson Sampling (CTS), which estimates the expected states of the arms via Thompson sampling, achieve bounded regret.
Context-Aware Hierarchical Online Learning for Performance Maximization in Mobile Crowdsourcing
In our algorithm, a local controller (LC) in the mobile device of a worker regularly observes the worker's context, her/his decisions to accept or decline tasks and the quality in completing tasks.
Gambler's Ruin Bandit Problem
In the GRBP, the learner proceeds in a sequence of rounds, where each round is a Markov Decision Process (MDP) with two actions (arms): a continuation action that moves the learner randomly over the state space around the current state; and a terminal action that moves the learner directly into one of the two terminal states (goal and dead-end state).
Adaptive Ensemble Learning with Confidence Bounds
Extracting actionable intelligence from distributed, heterogeneous, correlated and high-dimensional data sources requires run-time processing and learning both locally and globally.
Episodic Multi-armed Bandits
After the $stop$ action is taken, the learner collects a terminal reward, and observes the costs and terminal rewards associated with each step of the episode.
Global Bandits
In the case in which rewards of all arms are deterministic functions of a single unknown parameter, we construct a greedy policy that achieves {\em bounded regret}, with a bound that depends on the single true parameter of the problem.
Contextual Online Learning for Multimedia Content Aggregation
A key challenge for such systems is to accurately predict what type of content each of its consumers prefers in a certain context, and adapt these predictions to the evolving consumers' preferences, contexts and content characteristics.
RELEAF: An Algorithm for Learning and Exploiting Relevance
We prove a general regret bound for our algorithm whose time order depends only on the maximum number of relevant dimensions among all the actions, which in the special case where the relevance relation is single-valued (a function), reduces to $\tilde{O}(T^{2(\sqrt{2}-1)})$; in the absence of a relevance relation, the best known contextual bandit algorithms achieve regret $\tilde{O}(T^{(D+1)/(D+2)})$, where $D$ is the full dimension of the context vector.
Discovering, Learning and Exploiting Relevance
When the relation is a function, i. e., the reward of an action only depends on the context of a single type, and the expected reward of an action is Lipschitz continuous in the context of its relevant type, we propose an algorithm that achieves $\tilde{O}(T^{\gamma})$ regret with a high probability, where $\gamma=2/(1+\sqrt{2})$.
Jamming Bandits
We first present novel online learning algorithms to maximize the jamming efficacy against static transmitter-receiver pairs and prove that our learning algorithm converges to the optimal (in terms of the error rate inflicted at the victim and the energy used) jamming strategy.
Global Bandits with Holder Continuity
Specifically, we prove that the parameter-free (worst-case) regret is sublinear in time, and decreases with the informativeness of the arms.
Distributed Online Learning in Social Recommender Systems
In contrast to centralized recommender systems, in which there is a single centralized seller who has access to the complete inventory of items as well as the complete record of sales and user information, in decentralized recommender systems each seller/learner only has access to the inventory of items and user information for its own products and not the products and user information of other sellers, but can get commission if it sells an item of another seller.
Decentralized Online Big Data Classification - a Bandit Framework
We model the problem of joint classification by the distributed and heterogeneous learners from multiple data sources as a distributed contextual bandit problem where each data is characterized by a specific context.
Distributed Online Learning via Cooperative Contextual Bandits
At each moment of time, an instance characterized by a certain context may arrive to each learner; based on the context, the learner can select one of its own actions (which gives a reward and provides information) or request assistance from another learner.
Distributed Online Big Data Classification Using Context Information
Distributed, online data mining systems have emerged as a result of applications requiring analysis of large amounts of correlated and high-dimensional data produced by multiple distributed data sources.
Online Learning in a Contract Selection Problem
In an online contract selection problem there is a seller which offers a set of contracts to sequentially arriving buyers whose types are drawn from an unknown distribution.
Optimal Adaptive Learning in Uncontrolled Restless Bandit Problems
In an uncontrolled restless bandit problem, there is a finite set of arms, each of which when pulled yields a positive reward.
Online Algorithms for the Multi-Armed Bandit Problem with Markovian Rewards
The player receives a state-dependent reward each time it plays an arm.
