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 270 for “"Bandits"”.
-
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 …
-
BANDITS ROAMING HILBERT SPACE
… properties of quantum states using multi-armed bandits. Given streaming access to an unknown quantum state, in each round we select an observable from a set of actions to maximize its expectation value. Using past information, we refine actions to minimize regret—the cumulative gap between …
-
Non-linear contextual bandits
The multi-armed bandit framework can be motivated by any problem where there is an abundance of choice and the utility of trying something new must be balanced with that of going with the status quo. This is a trade-off that is present in the everyday problem of where and what to eat: should I try …
-
Communication-efficient multi-agent bandits
… the space of all possible decisions. Multi-armed bandits is one of the well-studied frameworks that captures this trade-off in a principled manner. Given the large volume of predictions made by these applications everyday, it becomes necessary to design learning algorithms that leverage …
-
Budget-limited multi-armed bandits
… under uncertainty abstractions, multi–armed bandits are perhaps one of the most common and best studied, as they present one of the clearest examples of the trade–off between exploration and exploitation. Whilst the standard bandit model has a broad applicability, it does not completely …
-
Bandits in autoregressive Markov models
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-08-01
-
EFFICIENCY AND REALISM IN STOCHASTIC BANDITS
… to the analysis of the application of stochastic bandits to the recommender systems domain. Here a learning agent sequentially recommends one item from a catalog of available alternatives. Consequently, the environment returns a reward that is a noisy observation of the rating associated to the …
-
Learning Techniques in Multi-Armed Bandits
… dilemma in which a collection of one-armed bandits, each with unknown but fixed reward probability, is given. The key idea is to develop a strategy, which results in the arm with the highest reward probability to be played such that the total reward obtained is maximized. Although seemingly …
-
Online advertisements and multi-armed bandits
… averages. Next, we consider multi-armed bandits with budgets, modeling how ad exchanges select which ad to display. We provide asymptotic regret lower bounds satisfied by any algorithm, and propose algorithms which match those lower bounds. We consider different types of budgets: …
-
Statistical miscellany: causality, networks, and bandits
In this dissertation, we make methodological contributions in three separate areas. In Chapter 2, we introduce a new algorithm for learning high-dimensional causal networks from observational data. Our algorithm, which is a simple modification to the well-known PC-Algorithm, provides reductions in …
-
Contextual Bandits with hard-safety constraints
Recently, Contextual Bandit algorithms with stage-wise constraints have attracted much attention due to their applicability in real-world contexts such as determining optimal dosages or ad policies. Nonetheless, a drawback is that they ensure high-probability guarantees only for the expected cost …
-
Adversarial Bandits and which Leader to Follow
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Locally Private and Robust Multi-Armed Bandits
… rewards in the context of multi-armed bandits (MABs). We consider two different practical settings: LDP-then-Corruption (LTC) where each user’s locally private response might be further corrupted during the data collection process, and Corruption-then-LDP (CTL) where each user’s raw …
-
Contextual Bandits with Neural Networks and Trees
… με την εκμετάλλευση (exploitation). Τα bandits παρέχουν ένα απλό μοντέλο για αυτό το δίλημμα. Τα contextual bandits αποτελούν μια πολύ σημαντική κατηγορία, όπου ο πράκτορας(agent) έχει πρόσβαση σε πρόσθετες πληροφορίες που μπορεί να βοηθήσουν στην πρόβλεψη της ποιότητας των ενεργειών …
-
Predictive adaptation of hybrid Monte Carlo with bandits
… Carlo (HMC) algorithm using Gaussian process bandits. HMC is a powerful Markov chain Monte Carlo (MCMC) method, but it requires careful tuning of its hyper-parameters. We propose a Gaussian process bandit approach to carry out the adaptation of the hyper-parameters while the Markov chain …
-
Contextual Bandits With Delayed Feedback Using Randomized Allocation
… bandit problems, the field of contextual bandits with delayed feedback, especially with nonparametric estimation tools, remains largely unexplored. In the first part of the dissertation, we study a simple randomized allocation strategy incorporating delayed feedback, and establish strong …
-
Swap-regret-minimizing bandits for distributed network optimization
Modern networked systems—ranging from real-time communication platforms to distributed computing infrastructures—operate in increasingly dynamic and strategic environments, where traditional optimization methods often fall short. This dissertation develops a new algorithmic framework for …
-
Multi-Armed Bandits with Risk-Aware Performance Measures
… Shortfall Lower Confidence Bound algorithm for bandits evaluated under Expected Shortfall, estab- lishing new concentration bounds for empirical Value at Risk and Expected Shortfall and deriving regret guarantees for both light- and heavy-tailed reward distributions. Building on this analysis, I …
-
Optimizing deep learning networks using multi-armed bandits
… those based on the following types of multi-arm bandits: (i) Epsilon-Greedy (ii) Upper Confidence Bounds (UCB) (iii) Thompson Sampling and (iv) Exponential Weight Algorithm for Exploration and Exploitation (EXP3). The algorithms were implemented in Python and a comprehensive empirical evaluation …
-
Certifying Warm Start Priors for Linear Contextual Bandits
Contextual bandits are a standard model for online recommendation systems, yet they often suffer from the cold start problem. Warm-starting has been used to alleviate this by pretraining a bandit with auxiliary information before it interacts with real users. Large language models (LLMs) have …
Page 1 of 14