We consider the k-armed stochastic contextual bandit problem with d dimensional features, when both k and d can be large. To the best of our knowledge, all existing algorithm for this problem have a regret bound that scale as polynomials of degree at least two in k and d. The main contribution of this paper is to introduce and theoretically analyze a new algorithm (REAL Bandit) with a regret that scales by r^2(k+d) when r is rank of the k by d matrix of unknown parameters. REAL Bandit relies on ideas from low-rank matrix estimation literature and a new row-enhancement subroutine that yields sharper bounds for estimating each row of the parameter matrix that may be of independent interest.

Summary: This paper studies the problem of regret minimization for low-rank linear contextual bandits. In the setting considered, there are k arms, each with an unknown d dimensional vector where k and d are assumed to be large. However, the k by d matrix of arms' feature vectors is assumed to be low rank with rank r, making some amount of information sharing for estimating different arms possible. At each time step, the algorithm proceeds as follows. First, a context is drawn iid from a distribution, similar to existing work.

We consider the k-armed stochastic contextual bandit problem with d dimensional features, when both k and d can be large. To the best of our knowledge, all existing algorithm for this problem have a regret bound that scale as polynomials of degree at least two in k and d. The main contribution of this paper is to introduce and theoretically analyze a new algorithm (REAL Bandit) with a regret that scales by r 2(k d) when r is rank of the k by d matrix of unknown parameters. REAL Bandit relies on ideas from low-rank matrix estimation literature and a new row-enhancement subroutine that yields sharper bounds for estimating each row of the parameter matrix that may be of independent interest.

Recently emerging large-scale biomedical data pose exciting opportunities for scientific discoveries. However, the ultrahigh dimensionality and non-negligible measurement errors in the data may create difficulties in estimation. There are limited methods for high-dimensional covariates with measurement error, that usually require knowledge of the noise distribution and focus on linear or generalized linear models. In this work, we develop high-dimensional measurement error models for a class of Lipschitz loss functions that encompasses logistic regression, hinge loss and quantile regression, among others. Our estimator is designed to minimize the $L_1$ norm among all estimators belonging to suitable feasible sets, without requiring any knowledge of the noise distribution. Subsequently, we generalize these estimators to a Lasso analog version that is computationally scalable to higher dimensions. We derive theoretical guarantees in terms of finite sample statistical error bounds and sign consistency, even when the dimensionality increases exponentially with the sample size. Extensive simulation studies demonstrate superior performance compared to existing methods in classification and quantile regression problems. An application to a gender classification task based on brain functional connectivity in the Human Connectome Project data illustrates improved accuracy under our approach, and the ability to reliably identify significant brain connections that drive gender differences.

We consider the k-armed stochastic contextual bandit problem with d dimensional features, when both k and d can be large. To the best of our knowledge, all existing algorithm for this problem have a regret bound that scale as polynomials of degree at least two in k and d. The main contribution of this paper is to introduce and theoretically analyze a new algorithm (REAL Bandit) with a regret that scales by r 2(k d) when r is rank of the k by d matrix of unknown parameters. REAL Bandit relies on ideas from low-rank matrix estimation literature and a new row-enhancement subroutine that yields sharper bounds for estimating each row of the parameter matrix that may be of independent interest. Papers published at the Neural Information Processing Systems Conference.

We propose and investigate a class of new algorithms for sequential decision making that interacts with \textit{a batch of users} simultaneously instead of \textit{a user} at each decision epoch. This type of batch models is motivated by interactive marketing and clinical trial, where a group of people are treated simultaneously and the outcomes of the whole group are collected before the next stage of decision. In such a scenario, our goal is to allocate a batch of treatments to maximize treatment efficacy based on observed high-dimensional user covariates. We deliver a solution, named \textit{Teamwork LASSO Bandit algorithm}, that resolves a batch version of explore-exploit dilemma via switching between teamwork stage and selfish stage during the whole decision process. This is made possible based on statistical properties of LASSO estimate of treatment efficacy that adapts to a sequence of batch observations. In general, a rate of optimal allocation condition is proposed to delineate the exploration and exploitation trade-off on the data collection scheme, which is sufficient for LASSO to identify the optimal treatment for observed user covariates. An upper bound on expected cumulative regret of the proposed algorithm is provided.

The purpose of this paper is to construct confidence intervals for the regression coefficients in the Fine-Gray model for competing risks data with random censoring, where the number of covariates can be larger than the sample size. Despite strong motivation from biostatistics applications, high-dimensional Fine-Gray model has attracted relatively little attention among the methodological or theoretical literatures. We fill in this blank by proposing first a consistent regularized estimator and then the confidence intervals based on the one-step bias-correcting estimator. We are able to generalize the partial likelihood approach for the Fine-Gray model under random censoring despite many technical difficulties. We lay down a methodological and theoretical framework for the one-step bias-correcting estimator with the partial likelihood, which does not have independent and identically distributed entries. We also handle for our theory the approximation error from the inverse probability weighting (IPW), proposing novel concentration results for time dependent processes. In addition to the theoretical results and algorithms, we present extensive numerical experiments and an application to a study of non-cancer mortality among prostate cancer patients using the linked Medicare-SEER data.