Decision-making in the face of uncertainty is a significant challenge in machine learning,
and the multi-armed bandit model is a commonly used framework to address it. This …

A fundamental challenge in contextual bandits is to develop flexible, general-purpose
algorithms with computational requirements no worse than classical supervised learning …

We study two randomized algorithms for generalized linear bandits. The first, GLM-TSL,
samples a generalized linear model (GLM) from the Laplace approximation to the posterior …

We consider reinforcement learning in an environment modeled by an episodic, tabular,
step-dependent Markov decision process of horizon $ H $ with $ S $ states, and $ A …

Abstract Upper Confidence Bound (UCB) method is arguably the most celebrated one used
in online decision making with partial information feedback. Existing techniques for …

We study the effects of approximate inference on the performance of Thompson sampling in
the $ k $-armed bandit problems. Thompson sampling is a successful algorithm for online …

Ensemble sampling serves as a practical approximation to Thompson sampling when
maintaining an exact posterior distribution over model parameters is computationally …

Clustering is a ubiquitous task in data science. Compared to the commonly used k-means
clustering, k-medoids clustering requires the cluster centers to be actual data points and …

We focus on a classic reinforcement learning problem, called a multi-armed bandit, and
more specifically in the stochastic setting with reward distributions bounded in $[0, 1] $. For …

Diffusion models excel at modeling complex data distributions, including those of images,
proteins, and small molecules. However, in many cases, our goal is to model parts of the …