We study matrix estimation problems arising in reinforcement learning with low-rank
structure. In low-rank bandits, the matrix to be recovered specifies the expected arm …

One of the central challenges in online advertising is attribution, namely, assessing the
contribution of individual advertiser actions including emails, display ads and search ads to …

Observations in various applications are frequently represented as a time series of
multidimensional arrays, called tensor time series, preserving the inherent multidimensional …

Contextual bandit has been widely used for sequential decision-making based on the
current contextual information and historical feedback data. In modern applications, such …

This paper studies a general framework for high-order tensor SVD. We propose a new
computationally efficient algorithm, tensor-train orthogonal iteration (TTOI), that aims to …

We consider the problem of model estimation in episodic Block MDPs. In these MDPs, the
decision maker has access to rich observations or contexts generated from a small number …

A block Markov chain is a Markov chain whose state space can be partitioned into a finite
number of clusters such that the transition probabilities only depend on the clusters. Block …

Sparsity-constraint optimization has wide applicability in signal processing, statistics, and
machine learning. Existing fast algorithms must burdensomely tune parameters, such as the …

Modern language models rely on the transformer architecture and attention mechanism to
perform language understanding and text generation. In this work, we study learning a 1 …

Multi-armed bandit (MAB) algorithms are efficient approaches to reduce the opportunity cost
of online experimentation and are used by companies to find the best product from …