
Optimal Accounting of Differential Privacy via Characteristic Function
Characterizing the privacy degradation over compositions, i.e., privacy ...
read it

Optimal Uniform OPE and Modelbased Offline Reinforcement Learning in TimeHomogeneous, RewardFree and TaskAgnostic Settings
This work studies the statistical limits of uniform convergence for offl...
read it

Optimal Dynamic Regret in ExpConcave Online Learning
We consider the problem of the Zinkevich (2003)style dynamic regret min...
read it

Logarithmic Regret in Featurebased Dynamic Pricing
Featurebased dynamic pricing is an increasingly popular model of settin...
read it

Nonstationary Online Learning with Memory and Nonstochastic Control
We study the problem of Online Convex Optimization (OCO) with memory, wh...
read it

NearOptimal Offline Reinforcement Learning via Double Variance Reduction
We consider the problem of offline reinforcement learning (RL) – a well...
read it

An Optimal Reduction of TVDenoising to Adaptive Online Learning
We consider the problem of estimating a function from n noisy samples wh...
read it

Revisiting ModelAgnostic Private Learning: Faster Rates and Active Learning
The Private Aggregation of Teacher Ensembles (PATE) framework is one of ...
read it

InterSeries Attention Model for COVID19 Forecasting
COVID19 pandemic has an unprecedented impact all over the world since e...
read it

Votingbased Approaches For Differentially Private Federated Learning
While federated learning (FL) enables distributed agents to collaborativ...
read it

Adaptive Online Estimation of Piecewise Polynomial Trends
We consider the framework of nonstationary stochastic optimization [Bes...
read it

Near Optimal Provable Uniform Convergence in OffPolicy Evaluation for Reinforcement Learning
The OffPolicy Evaluation aims at estimating the performance of target p...
read it

Bullseye Polytope: A Scalable CleanLabel Poisoning Attack with Improved Transferability
A recent source of concern for the security of neural networks is the em...
read it

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
Adversarial learning has demonstrated good performance in the unsupervis...
read it

Asymptotically Efficient OffPolicy Evaluation for Tabular Reinforcement Learning
We consider the problem of offpolicy evaluation for reinforcement learn...
read it

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Time series forecasting is an important problem across many domains, inc...
read it

Doubly Robust Crowdsourcing
Largescale labeled datasets are the indispensable fuel that ignites the...
read it

Optimal OffPolicy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Motivated by the many realworld applications of reinforcement learning ...
read it

Online Forecasting of TotalVariationbounded Sequences
We consider the problem of online forecasting of sequences of length n w...
read it

Provably Efficient QLearning with Low Switching Cost
We take initial steps in studying PACMDP algorithms with limited adapti...
read it

A HigherOrder KolmogorovSmirnov Test
We present an extension of the KolmogorovSmirnov (KS) twosample test, ...
read it

ImitationRegularized Offline Learning
We study the problem of offline learning in automated decision systems u...
read it

ProxQuant: Quantized Neural Networks via Proximal Operators
To make deep neural networks feasible in resourceconstrained environmen...
read it

Subsampled Rényi Differential Privacy and Analytical Moments Accountant
We study the problem of subsampling in differential privacy (DP), a ques...
read it

Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
The Gaussian mechanism is an essential building block used in multitude ...
read it

Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain
We revisit the problem of linear regression under a differential privacy...
read it

signSGD: compressed optimisation for nonconvex problems
Training large neural networks requires distributing learning across mul...
read it

Detecting and Correcting for Label Shift with Black Box Predictors
Faced with distribution shift between training and test set, we wish to ...
read it

Nonstationary Stochastic Optimization with Local Spatial and Temporal Changes
We consider a nonstationary sequential stochastic optimization problem,...
read it

Perinstance Differential Privacy and the Adaptivity of Posterior Sampling in Linear and Ridge regression
Differential privacy (DP), ever since its advent, has been a controversi...
read it

Understanding the 2016 US Presidential Election using ecological inference and distribution regression with census microdata
We combine finegrained spatially referenced census data with the vote o...
read it

A Theoretical Analysis of Noisy Sparse Subspace Clustering on DimensionalityReduced Data
Subspace clustering is the problem of partitioning unlabeled data points...
read it

Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers
We consider the problem of estimating a function defined over n location...
read it

OnAverage KLPrivacy and its equivalence to Generalization for MaxEntropy Mechanisms
We define OnAverage KLPrivacy and present its properties and connectio...
read it

A Minimax Theory for Adaptive Data Analysis
In adaptive data analysis, the user makes a sequence of queries on the d...
read it

Fast Differentially Private Matrix Factorization
Differentially private collaborative filtering is a challenging task, bo...
read it

Graph Connectivity in Noisy Sparse Subspace Clustering
Subspace clustering is the problem of clustering data points into a unio...
read it

Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo
We consider the problem of Bayesian learning on sensitive datasets and p...
read it

Learning with Differential Privacy: Stability, Learnability and the Sufficiency and Necessity of ERM Principle
While machine learning has proven to be a powerful datadriven solution ...
read it

Trend Filtering on Graphs
We introduce a family of adaptive estimators on graphs, based on penaliz...
read it

Parallel and Distributed BlockCoordinate FrankWolfe Algorithms
We develop parallel and distributed FrankWolfe algorithms; the former o...
read it

The Falling Factorial Basis and Its Statistical Applications
We study a novel splinelike basis, which we name the "falling factorial...
read it

Practical Matrix Completion and Corruption Recovery using Proximal Alternating Robust Subspace Minimization
Lowrank matrix completion is a problem of immense practical importance....
read it

Noisy Sparse Subspace Clustering
This paper considers the problem of subspace clustering under noise. Spe...
read it
YuXiang Wang
is this you? claim profile
Scientist, Amazon AI, AWS, Applied Scientist, Amazon AI, Machine Learning Department in Carnegie Mellon University, PhD Student at Carnegie Mellon University.