b'Yu-Xiang Wang'

research

∙ 08/30/2023

Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation

Data valuation, a critical aspect of data-centric ML research, aims to q...

0 Jiachen T. Wang, et al. ∙

research

∙ 08/17/2023

Model-Free Algorithm with Improved Sample Efficiency for Zero-Sum Markov Games

The problem of two-player zero-sum Markov games has recently attracted i...

0 Songtao Feng, et al. ∙

research

∙ 07/04/2023

Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks

Convolutional residual neural networks (ConvResNets), though overparamet...

0 Kaiqi Zhang, et al. ∙

research

∙ 06/30/2023

Provable Robust Watermarking for AI-Generated Text

As AI-generated text increasingly resembles human-written content, the a...

0 Xuandong Zhao, et al. ∙

research

∙ 06/24/2023

Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data

Developing theoretical guarantees on the sample complexity of offline RL...

0 Sunil Madhow, et al. ∙

research

∙ 06/12/2023

"Private Prediction Strikes Back!” Private Kernelized Nearest Neighbors with Individual Renyi Filter

Most existing approaches of differentially private (DP) machine learning...

0 Yuqing Zhu, et al. ∙

research

∙ 06/02/2023

Generative Autoencoders as Watermark Attackers: Analyses of Vulnerabilities and Threats

Invisible watermarks safeguard images' copyrights by embedding hidden me...

0 Xuandong Zhao, et al. ∙

research

∙ 06/01/2023

Non-stationary Reinforcement Learning under General Function Approximation

General function approximation is a powerful tool to handle large state ...

0 Songtao Feng, et al. ∙

research

∙ 05/31/2023

Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms

This paper focuses on supervised and unsupervised online label shift, wh...

0 Dheeraj Baby, et al. ∙

research

∙ 03/06/2023

Improved Differentially Private Regression via Gradient Boosting

We revisit the problem of differentially private squared error linear re...

0 Shuai Tang, et al. ∙

research

∙ 02/26/2023

No-Regret Linear Bandits beyond Realizability

We study linear bandits when the underlying reward function is not linea...

0 Chong Liu, et al. ∙

research

∙ 02/24/2023

Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs

In many real-life reinforcement learning (RL) problems, deploying new po...

0 Dan Qiao, et al. ∙

research

∙ 02/06/2023

Protecting Language Generation Models via Invisible Watermarking

Language generation models have been an increasingly powerful enabler fo...

0 Xuandong Zhao, et al. ∙

research

∙ 12/31/2022

Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy

The ”Propose-Test-Release” (PTR) framework is a classic recipe for desig...

1 Rachel Redberg, et al. ∙

research

∙ 12/09/2022

Near-Optimal Differentially Private Reinforcement Learning

Motivated by personalized healthcare and other applications involving se...

0 Dan Qiao, et al. ∙

research

∙ 11/16/2022

Global Optimization with Parametric Function Approximation

We consider the problem of global optimization with noisy zeroth order o...

0 Chong Liu, et al. ∙

research

∙ 10/07/2022

Distillation-Resistant Watermarking for Model Protection in NLP

How can we protect the intellectual property of trained NLP models? Mode...

0 Xuandong Zhao, et al. ∙

research

∙ 10/03/2022

Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient

Offline reinforcement learning, which aims at optimizing sequential deci...

0 Ming Yin, et al. ∙

research

∙ 10/03/2022

Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation

We study the problem of deployment efficient reinforcement learning (RL)...

0 Dan Qiao, et al. ∙

research

∙ 09/30/2022

Differentially Private Optimization on Large Model at Small Cost

Differentially private (DP) optimization is the standard paradigm to lea...

0 Zhiqi Bu, et al. ∙

research

∙ 09/30/2022

Differentially Private Bias-Term only Fine-tuning of Foundation Models

We study the problem of differentially private (DP) fine-tuning of large...

0 Zhiqi Bu, et al. ∙

research

∙ 09/23/2022

Doubly Fair Dynamic Pricing

We study the problem of online dynamic pricing with two types of fairnes...

0 Jianyu Xu, et al. ∙

research

∙ 06/18/2022

Optimal Dynamic Regret in LQR Control

We consider the problem of nonstochastic control with a sequence of quad...

0 Dheeraj Baby, et al. ∙

research

∙ 06/14/2022

Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger

Per-example gradient clipping is a key algorithmic step that enables pra...

0 Zhiqi Bu, et al. ∙

research

∙ 06/13/2022

Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks

Quantized neural networks have drawn a lot of attention as they reduce t...

0 Kaiqi Zhang, et al. ∙

research

∙ 06/10/2022

Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality

Goal-oriented Reinforcement Learning, where the agent needs to reach the...

0 Ming Yin, et al. ∙

research

∙ 06/02/2022

Offline Reinforcement Learning with Differential Privacy

The offline reinforcement learning (RL) problem is often motivated by th...

0 Dan Qiao, et al. ∙

research

∙ 05/19/2022

Differentially Private Linear Sketches: Efficient Implementations and Applications

Linear sketches have been widely adopted to process fast data streams, a...

0 Fuheng Zhao, et al. ∙

research

∙ 05/04/2022

Second Order Path Variationals in Non-Stationary Online Learning

We consider the problem of universal dynamic regret minimization under e...

0 Dheeraj Baby, et al. ∙

research

∙ 05/04/2022

Provably Confidential Language Modelling

Large language models are shown to memorize privacy information such as ...

0 Xuandong Zhao, et al. ∙

research

∙ 04/20/2022

Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?

We study the theory of neural network (NN) from the lens of classical no...

0 Kaiqi Zhang, et al. ∙

research

∙ 03/30/2022

Towards Differential Relational Privacy and its use in Question Answering

Memorization of the relation between entities in a dataset can lead to p...

0 Simone Bombari, et al. ∙

research

∙ 03/30/2022

Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE

We provide an end-to-end Renyi DP based-framework for differentially pri...

0 Yuqing Zhu, et al. ∙

research

∙ 03/22/2022

Mixed Differential Privacy in Computer Vision

We introduce AdaMix, an adaptive differentially private algorithm for tr...

18 Aditya Golatkar, et al. ∙

research

∙ 03/11/2022

Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism

Offline reinforcement learning, which seeks to utilize offline/historica...

0 Ming Yin, et al. ∙

research

∙ 02/13/2022

Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost

We study the problem of reinforcement learning (RL) with low (policy) sw...

0 Dan Qiao, et al. ∙

research

∙ 01/27/2022

Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise

In feature-based dynamic pricing, a seller sets appropriate prices for a...

0 Jianyu Xu, et al. ∙

research

∙ 01/21/2022

Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond

We study the framework of universal dynamic regret minimization with str...

0 Dheeraj Baby, et al. ∙

research

∙ 12/29/2021

Multivariate Trend Filtering for Lattice Data

We study a multivariate version of trend filtering, called Kronecker tre...

13 Veeranjaneyulu Sadhanala, et al. ∙

research

∙ 11/03/2021

Privately Publishable Per-instance Privacy

We consider how to privately share the personalized privacy losses incur...

0 Rachel Redberg, et al. ∙

research

∙ 10/17/2021

Towards Instance-Optimal Offline Reinforcement Learning with Pessimism

We study the offline reinforcement learning (offline RL) problem, where ...

0 Ming Yin, et al. ∙

research

∙ 06/16/2021

Optimal Accounting of Differential Privacy via Characteristic Function

Characterizing the privacy degradation over compositions, i.e., privacy ...

0 Yuqing Zhu, et al. ∙

research

∙ 05/13/2021

Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings

This work studies the statistical limits of uniform convergence for offl...

0 Ming Yin, et al. ∙

research

∙ 04/23/2021

Optimal Dynamic Regret in Exp-Concave Online Learning

We consider the problem of the Zinkevich (2003)-style dynamic regret min...

0 Dheeraj Baby, et al. ∙

research

∙ 02/20/2021

Logarithmic Regret in Feature-based Dynamic Pricing

Feature-based dynamic pricing is an increasingly popular model of settin...

0 Jianyu Xu, et al. ∙

research

∙ 02/07/2021

Non-stationary Online Learning with Memory and Non-stochastic Control

We study the problem of Online Convex Optimization (OCO) with memory, wh...

0 Peng Zhao, et al. ∙

research

∙ 02/02/2021

Near-Optimal Offline Reinforcement Learning via Double Variance Reduction

We consider the problem of offline reinforcement learning (RL) – a well-...

45 Ming Yin, et al. ∙

research

∙ 01/23/2021

An Optimal Reduction of TV-Denoising to Adaptive Online Learning

We consider the problem of estimating a function from n noisy samples wh...

0 Dheeraj Baby, et al. ∙

research

∙ 11/06/2020

Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning

The Private Aggregation of Teacher Ensembles (PATE) framework is one of ...

0 Chong Liu, et al. ∙

research

∙ 10/25/2020

Inter-Series Attention Model for COVID-19 Forecasting

COVID-19 pandemic has an unprecedented impact all over the world since e...

0 Xiaoyong Jin, et al. ∙

Yu-Xiang Wang

Featured Co-authors