Concentration inequalities for statistical inference

H Zhang, SX Chen - ar** upper confidence bound
B Hao, Y Abbasi Yadkori, Z Wen… - Advances in neural …, 2019 - proceedings.neurips.cc
Abstract Upper Confidence Bound (UCB) method is arguably the most celebrated one used
in online decision making with partial information feedback. Existing techniques for …

Computational limits of a distributed algorithm for smoothing spline

Z Shang, G Cheng - Journal of Machine Learning Research, 2017 - jmlr.org
In this paper, we explore statistical versus computational trade-off to address a basic
question in the application of a distributed algorithm: what is the minimal computational cost …

Frequentist coverage and sup-norm convergence rate in Gaussian process regression

Y Yang, A Bhattacharya, D Pati - arxiv preprint arxiv:1708.04753, 2017 - arxiv.org
Gaussian process (GP) regression is a powerful interpolation technique due to its flexibility
in capturing non-linearity. In this paper, we provide a general framework for understanding …

Growing-dimensional partially functional linear models: non-asymptotic optimal prediction error

H Zhang, X Lei - Physica Scripta, 2023 - iopscience.iop.org
Under the reproducing kernel Hilbert spaces (RKHS), we focus on the penalized least-
squares of the partially functional linear models (PFLM), whose predictor contains both …

A theoretical framework of the scaled Gaussian stochastic process in prediction and calibration

M Gu, F **e, L Wang - SIAM/ASA Journal on Uncertainty Quantification, 2022 - SIAM
Model calibration or data inversion is one of the fundamental tasks in uncertainty
quantification. In this work, we study the theoretical properties of the scaled Gaussian …

Tight non-asymptotic inference via sub-Gaussian intrinsic moment norm

H Zhang, H Wei, G Cheng - arxiv preprint arxiv:2303.07287, 2023 - arxiv.org
In non-asymptotic learning, variance-type parameters of sub-Gaussian distributions are of
paramount importance. However, directly estimating these parameters using the empirical …

A multiplier bootstrap approach to designing robust algorithms for contextual bandits

H **e, Q Tang, Q Zhu - IEEE Transactions on Neural Networks …, 2022 - ieeexplore.ieee.org
Upper confidence bound (UCB)-based contextual bandit algorithms require one to know the
tail property of the reward distribution. Unfortunately, such tail property is usually unknown or …

Non-asymptotic optimal prediction error for growing-dimensional partially functional linear models

H Zhang, X Lei - arxiv preprint arxiv:2009.04729, 2020 - arxiv.org
Under the reproducing kernel Hilbert spaces (RKHS), we consider the penalized least-
squares of the partially functional linear models (PFLM), whose predictor contains both …

How many machines can we use in parallel computing for kernel ridge regression?

M Liu, Z Shang, G Cheng - arxiv preprint arxiv:1805.09948, 2018 - arxiv.org
This paper aims to solve a basic problem in distributed statistical inference: how many
machines can we use in parallel computing? In kernel ridge regression, we address this …