Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 87 for “"bandit problem"”.
-
Nonparametric Estimation and Model Combination in a Bandit Problem with Covariates
Multi-armed bandit problem is an important optimization game that requires an exploration-exploitation tradeoff to achieve optimal total reward. Motivated from industrial applications such as online advertising and clinical research, we consider a setting where the rewards of bandit machines are …
-
Comparison of Arm Selection Policies for the Multi-Armed Bandit Problem
… and satisfaction. Contextual multi-armed bandit provides several strategies to address this online decision-making problem at a lower experimental cost than traditional A/B testing. In this study, we compare three common Contextual Bandit strategies that exist in literature namely …
-
Mathematical properties of the Stochastic Approximation and the Multi-Armed Bandit problem
… Κεφάλαιο 4, μελετάμε το πρόβλημα των multi-armed bandit, το αντικείμενο του οποίου είναι ο προσδιορισμός της πιο κερδοφόρας δράσης από ένα δοσμένο σύνολο, μαζί με την ταυτόχρονη μεγιστοποίηση του αναμενόμενου κέρδους μας σε βάθος χρόνου. Αποδεικνύουμε το φράγμα των Lai-Robbins, σύμφωνα με το οποίο …
-
THE CONFIDENCE BOUND METHOD FOR THE MULTI-ARMED BANDIT PROBLEM WITH LARGE ARM SIZE
We consider two modifications of the confidence bound method that achieve optimality in the case of large arm sizes. In the first situation we assume the arm size is infinitely large. We establish a regret lower bound and construct confidence bounds that achieve the regret lower bound …
-
A Control Theoretic Approach to the Stochastic Multi-armed Bandit Problem With Applications in Hyperparameter Optimization
… under uncertainty is a fundamental problem encountered frequently in many real-world applications. This challenge has been rigorously formulated as the Stochastic Multi-Armed Bandit (SMAB) problem, which consists of a learner interacting with an environment. For each interaction, the …
-
Learning in three classic bandit strategies
In a Bandit Problem one is repeatedly asked to implement one of a set of actions each of which produce some observable long term behaviour, and one aims to achieve some objective such as maximisation of a reward stream, or consistency. The fundamental dilema one must address is when to choose to …
-
Stochastic control approach to the multi-armed bandit problems
<p>A multi-armed bandit is the simplest problem to study learning under uncertainty when decisions affect information. A standard approach to the multi-armed bandit often gives a heuristic construction of an algorithm and proves its regret bound. Following a constructive approach, it is often …
-
Data-Efficient Decision-Making
… and offline (batch) settings: (i) What problem structures allow for achieving instance-specific fast regret rates? (ii) How can these problem structures be leveraged to design \textit{practical} algorithms that achieve fast theoretical rates? Part I of this thesis investigates the above …
-
Constrained learning in the bandit setting: doubly optimistic strategies and fast rates
The (stochastic) bandit problem is a classic example used to address the challenge of balancing exploration and exploitation when dealing with bandit feedback. This dissertation focuses on stochastic bandits with constraints, where each action (or arm) bears both a reward and a safety risk. The …
-
Statistical Theory for Sequential Decision-Making: Multiple Testing and High-Dimensional Linear Contextual Bandits
… testing and high-dimensional linear contextual bandits. For the sequential multiple testing problem, we develop a unified theory of second-order asymptotic optimality. We establish general sufficient conditions under which second-order Bayesian optimality implies second-order frequentist …
-
Multi-Armed Bandits with Risk-Aware Performance Measures
The classical multi-armed bandit problem involves a learner and a collection of arms with unknown reward distributions. At each round, the learner selects an arm and receives new information. The learner faces a tradeoff between exploiting the current information and exploring all arms. The …
-
Thresholded linear bandits
Thresholded linear bandits is a novel bandit problem that lies in the intersection of several important multiarmed bandit (MAB) variants, including active learning, structured bandits, and learning halfspaces. To achieve sublinear regret in the presence of exponentially many arms, one method is to …
-
Optimal Learning with Non-Gaussian Rewards
… the author studies sequential Bayesian learning problems modeled under non-Gaussian distributions. We focus on a class of problems called the multi-armed bandit problem, and studies its optimal learning strategy, the Gittins index policy. The Gittins index is computationally intractable and …
-
Sequential Decision Making With Resource Constraints
… making with partial feedback is the multi-armed bandit problem. This model has also found applications to a very diverse set of problems such as sequential design of experiments including medical decision-making, learning click-through rates in search engines, economic theory, network routing, …
-
LEARNING UNDER STRUCTURE AND UNCERTAINTY: ALGORITHMS FOR BANDIT AND ONLINE DECISION MAKING
… with a particular focus on the multi-armed bandit and online learning frameworks. At the core of these settings lies a simple yet powerful interaction protocol: at each round the learner receives a question (information available prior to a decision), provides an answer (an action or …
-
Acceleration in first-order optimization methods: promenading beyond convexity or smoothness, and applications
… over other more simple algorithms for the same problem. For example, Nesterov's Accelerated Gradient Descent improves over the gradient descent method for the optimization of smooth and convex functions. In this thesis, we investigate the acceleration phenomenon and its applications for three …
-
Dynamic decision behavior: Competitive tests of decision policies in a class of two-armed bandit problems
The Two-Armed Bandit Problem (TAB) is an individual decision making problem that is dynamic in nature. In a dynamic task, stage-to-stage changes in the state of the system are affected by the decision-maker's (DM) previous decisions as well as by the states of the system at the preceding stages. …
-
PERFORMANCE GUARANTEES FOR ONLINE LEARNING: CASCADING BANDITS AND ADVERSARIAL CORRUPTIONS
The multi-armed bandit problem (MAB) is an important online learning problem that exemplifies the dilemma between exploration and exploitation in sequential decision making. We explore different objectives for several settings of the MAB problem. Firstly, the prevalence of online recommender …
-
Efficient Text-Image Retrieval Using Large Language Models
… and models candidate selection as a multi-armed bandit problem. Each cluster acts as an arm, with relevance scores from ground-truth systems as rewards. Using Thompson Sampling, this approach balances exploration and exploitation to quickly identify promising clusters, reducing unnecessary …
Page 1 of 5