1.1k citations · 2.4k across the 69 of their papers we have counts for
44 papers · 1 filter
Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation
Jiachen T. Wang, Yuqing Zhu, Yu-Xiang Wang +2
Data valuation aims to quantify the usefulness of individual data sources in training machine learning (ML) models, and is a critical aspect of data-centric ML research. However, d…
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
Zixuan Zhang, Kaiqi Zhang, Minshuo Chen +4
Convolutional residual neural networks (ConvResNets), though overparameterized, can achieve remarkable prediction performance in practice, which cannot be well explained by convent…
Improved Differentially Private Regression via Gradient Boosting
Shuai Tang, Sergul Aydore, Michael Kearns +5
We revisit the problem of differentially private squared error linear regression. We observe that existing state-of-the-art methods are sensitive to the choice of hyperparameters -…
Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy
Rachel Redberg, Yuqing Zhu, Yu-Xiang Wang
The ''Propose-Test-Release'' (PTR) framework is a classic recipe for designing differentially private (DP) algorithms that are data-adaptive, i.e. those that add less noise when th…
Global Optimization with Parametric Function Approximation
Chong Liu, Yu-Xiang Wang
We consider the problem of global optimization with noisy zeroth order oracles - a well-motivated problem useful for various applications ranging from hyper-parameter tuning for de…
Differentially Private Optimization on Large Model at Small Cost
Zhiqi Bu, Yu-Xiang Wang, Sheng Zha +1
Differentially private (DP) optimization is the standard paradigm to learn large neural networks that are accurate and privacy-preserving. The computational cost for DP deep learni…
Differentially Private Bias-Term Fine-tuning of Foundation Models
Zhiqi Bu, Yu-Xiang Wang, Sheng Zha +1
We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a recent privacy-preserving approach suitable for solving downstream tasks with sensi…
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks
Kaiqi Zhang, Ming Yin, Yu-Xiang Wang
Quantized neural networks have drawn a lot of attention as they reduce the space and computational complexity during the inference. Moreover, there has been folklore that quantizat…
Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger
Zhiqi Bu, Yu-Xiang Wang, Sheng Zha +1
Per-example gradient clipping is a key algorithmic step that enables practical differential private (DP) training for deep learning models. The choice of clipping threshold R, howe…
Second Order Path Variationals in Non-Stationary Online Learning
Dheeraj Baby, Yu-Xiang Wang
We consider the problem of universal dynamic regret minimization under exp-concave and smooth losses. We show that appropriately designed Strongly Adaptive algorithms achieve a dyn…
Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?
Kaiqi Zhang, Yu-Xiang Wang
We study the theory of neural network (NN) from the lens of classical nonparametric regression problems with a focus on NN's ability to adaptively estimate functions with heterogen…
Towards Differential Relational Privacy and its use in Question Answering
Simone Bombari, Alessandro Achille, Zijian Wang +6
Memorization of the relation between entities in a dataset can lead to privacy issues when using a trained model for question answering. We introduce Relational Memorization (RM) t…
Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE
Yuqing Zhu, Yu-Xiang Wang
We provide an end-to-end Renyi DP based-framework for differentially private top- selection. Unlike previous approaches, which require a data-independent choice on , we propo…
Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism
Ming Yin, Yaqi Duan, Mengdi Wang +1
Offline reinforcement learning, which seeks to utilize offline/historical data to optimize sequential decision-making strategies, has gained surging prominence in recent studies. D…
Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
Dan Qiao, Ming Yin, Ming Min +1
We study the problem of reinforcement learning (RL) with low (policy) switching cost - a problem well-motivated by real-life RL applications in which deployments of new policies ar…
Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond
Dheeraj Baby, Yu-Xiang Wang
We study the framework of universal dynamic regret minimization with strongly convex losses. We answer an open problem in Baby and Wang 2021 by showing that in a proper learning se…
Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise
Jianyu Xu, Yu-Xiang Wang
In feature-based dynamic pricing, a seller sets appropriate prices for a sequence of products (described by feature vectors) on the fly by learning from the binary outcomes of prev…
Towards Instance-Optimal Offline Reinforcement Learning with Pessimism
Ming Yin, Yu-Xiang Wang
We study the offline reinforcement learning (offline RL) problem, where the goal is to learn a reward-maximizing policy in an unknown Markov Decision Process (MDP) using the data c…
Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings
Ming Yin, Yu-Xiang Wang
This work studies the statistical limits of uniform convergence for offline policy evaluation (OPE) problems with model-based methods (for episodic MDP) and provides a unified fram…
Optimal Accounting of Differential Privacy via Characteristic Function
Yuqing Zhu, Jinshuo Dong, Yu-Xiang Wang
Characterizing the privacy degradation over compositions, i.e., privacy accounting, is a fundamental topic in differential privacy (DP) with many applications to differentially pri…
Optimal Dynamic Regret in Exp-Concave Online Learning
Dheeraj Baby, Yu-Xiang Wang
We consider the problem of the Zinkevich (2003)-style dynamic regret minimization in online learning with exp-concave losses. We show that whenever improper learning is allowed, a…
Near-Optimal Offline Reinforcement Learning via Double Variance Reduction
Ming Yin, Yu Bai, Yu-Xiang Wang
We consider the problem of offline reinforcement learning (RL) -- a well-motivated setting of RL that aims at policy optimization using only historical data. Despite its wide appli…
Logarithmic Regret in Feature-based Dynamic Pricing
Jianyu Xu, Yu-Xiang Wang
Feature-based dynamic pricing is an increasingly popular model of setting prices for highly differentiated products with applications in digital marketing, online sales, real estat…
Non-stationary Online Learning with Memory and Non-stochastic Control
Peng Zhao, Yu-Hu Yan, Yu-Xiang Wang +1
We study the problem of Online Convex Optimization (OCO) with memory, which allows loss functions to depend on past decisions and thus captures temporal effects of learning problem…