1 citations · 1 across the 13 of their papers we have counts for
14 papers
Fourth-Moment Geometry of Rademacher Sums
Peigan Gao, Jian Qian
Let be independent Rademacher signs and let satisfy the normalization below. For the normalized Rademacher sum, we…
An Optimal Agnostic PAC Algorithm
Markus Engelund Mathiasen, Jian Qian, Nikita Zhivotovskiy
Let be a class of finite VC dimension . Writing for the binary risk and , we construct a learner achieving the statistical…
Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression
Fan Chen, Jian Qian, Alexander Rakhlin +1
Self-normalized martingale inequalities lie at the heart of confidence ellipsoids for online least squares and, more broadly, many bandit and reinforcement-learning results. Yet ex…
Ratio Covers of Convex Sets and Optimal Mixture Density Estimation
Spencer Compton, Gábor Lugosi, Jaouad Mourtada +2
We study density estimation in Kullback-Leibler divergence: given an i.i.d. sample from an unknown density , the goal is to construct an estimator such that…
Multiplicative Oracle Inequalities for Transductive Learning via Level-Set Aggregation
Jian Qian, Jiachen Xu
We revisit transductive learning where predictions are made with the set of all covariates known in advance. In the leave-one-out (LOO) setting, the prediction is made with labels…
Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses
Jian Qian, Chen-Yu Wei
In adversarial multi-armed bandits, two performance measures are commonly used: static regret, which compares the learner to the best fixed arm, and dynamic regret, which compares…
Data Reconstruction: Identifiability and Optimization with Sample Splitting
Yujie Shen, Zihan Wang, Jian Qian +1
Training data reconstruction from KKT conditions has shown striking empirical success, yet it remains unclear when the resulting KKT equations have unique solutions and, even in id…
Sigmoid-FTRL: Design-Based Adaptive Neyman Allocation for AIPW Estimators
Fangyi Chen, Shu Ge, Jian Qian +1
We consider the problem of Adaptive Neyman Allocation for the class of AIPW estimators in a design-based setting, where potential outcomes and covariates are deterministic. As each…
Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits
Yuzhou Gu, Yanjun Han, Jian Qian
We study the evolution of information in interactive decision making through the lens of a stochastic multi-armed bandit problem. Focusing on a fundamental example where a unique o…
How Does Variance Shape the Regret in Contextual Bandits?
Zeyu Jia, Jian Qian, Alexander Rakhlin +1
We consider realizable contextual bandits with general function approximation, investigating how small reward variance can lead to better-than-minimax regret bounds. Unlike in mini…
Refined Risk Bounds for Unbounded Losses via Transductive Priors
Jian Qian, Alexander Rakhlin, Nikita Zhivotovskiy
We revisit the sequential variants of linear regression with the squared loss, classification problems with hinge loss, and logistic regression, all characterized by unbounded loss…
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
Fan Chen, Dylan J. Foster, Yanjun Han +3
We develop a unifying framework for information-theoretic lower bound in statistical estimation and interactive decision making. Classical lower bound techniques -- such as Fano's…
Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
Jian Qian, Haichen Hu, David Simchi-Levi
Motivated by the recent discovery of a statistical and computational reduction from contextual bandits to offline regression (Simchi-Levi and Xu, 2021), we address the general (sto…
Online Estimation via Offline Estimation: An Information-Theoretic Framework
Dylan J. Foster, Yanjun Han, Jian Qian +1
The classical theory of statistical estimation aims to estimate a parameter of interest under data generated from a fixed design ("offline estimation"), while the contemporary t…