Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Khamaru, Koulik"'
Autor:
Khamaru, Koulik, Zhang, Cun-Hui
In this paper, we discuss the asymptotic behavior of the Upper Confidence Bound (UCB) algorithm in the context of multiarmed bandit problems and discuss its implication in downstream inferential tasks. While inferential tasks become challenging when
Externí odkaz:
http://arxiv.org/abs/2408.04595
Weighted conformal prediction (WCP), a recently proposed framework, provides uncertainty quantification with the flexibility to accommodate different covariate distributions between training and test data. However, it is pointed out in this paper tha
Externí odkaz:
http://arxiv.org/abs/2405.06479
Autor:
Khamaru, Koulik
We consider the problem of stochastic convex optimization under convex constraints. We analyze the behavior of a natural variance reduced proximal gradient (VRPG) algorithm for this problem. Our main result is a non-asymptotic guarantee for VRPG algo
Externí odkaz:
http://arxiv.org/abs/2404.00042
Estimation and inference in statistics pose significant challenges when data are collected adaptively. Even in linear models, the Ordinary Least Squares (OLS) estimator may fail to exhibit asymptotic normality for single coordinate estimation and hav
Externí odkaz:
http://arxiv.org/abs/2310.00532
Sequential data collection has emerged as a widely adopted technique for enhancing the efficiency of data gathering processes. Despite its advantages, such data collection mechanism often introduces complexities to the statistical inference procedure
Externí odkaz:
http://arxiv.org/abs/2307.07320
Many standard estimators, when applied to adaptively collected data, fail to be asymptotically normal, thereby complicating the construction of confidence intervals. We address this challenge in a semi-parametric context: estimating the parameter vec
Externí odkaz:
http://arxiv.org/abs/2303.02534
Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. Such problem-dependent behavior is not captured by worst-case analyses and has accordingly inspired a growing
Externí odkaz:
http://arxiv.org/abs/2201.08536
We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. Focusing on a stochastic query model that provides noisy evaluations of the operator, we analyze a variance-reduced stochastic approxima
Externí odkaz:
http://arxiv.org/abs/2201.08518
When data is collected in an adaptive manner, even simple methods like ordinary least squares can exhibit non-normal asymptotic behavior. As an undesirable consequence, hypothesis tests and confidence intervals based on asymptotic normality can lead
Externí odkaz:
http://arxiv.org/abs/2107.02266
Various algorithms in reinforcement learning exhibit dramatic variability in their convergence rates and ultimate accuracy as a function of the problem structure. Such instance-specific behavior is not captured by existing global minimax bounds, whic
Externí odkaz:
http://arxiv.org/abs/2106.14352