Supervised learning aims to train a classifier under the assumption that training and test
data are from the same distribution. To ease the above assumption, researchers have …

As machine learning systems grow in scale, so do their training data requirements, forcing
practitioners to automate and outsource the curation of training data in order to achieve state …

In learning with noisy labels, the sample selection approach is very popular, which regards
small-loss data as correctly labeled during training. However, losses are generated on-the …

We study the relationship between adversarial robustness and differential privacy in high-
dimensional algorithmic statistics. We give the first black-box reduction from privacy to …

We introduce a universal framework for characterizing the statistical efficiency of a statistical
estimation problem with differential privacy guarantees. Our framework, which we call High …

We give the first polynomial-time algorithm to estimate the mean of ad-variate probability
distribution with bounded covariance from Õ (d) independent samples subject to pure …

In this work, we give efficient algorithms for privately estimating a Gaussian distribution in
both pure and approximate differential privacy (DP) models with optimal dependence on the …

In statistical learning and analysis from shared data, which is increasingly widely adopted in
platforms such as federated learning and meta-learning, there are two major concerns …

Dataset distillation has emerged as a prominent technique to improve data efficiency when
training machine learning models. It encapsulates the knowledge from a large dataset into a …

We construct an algorithm for estimating the mean of a heavy-tailed random variable when
given an adversarial corrupted sample of N independent observations. The only assumption …