English
Related papers

Related papers: The Sample Complexity of Distribution-Free Parity …

200 papers

We show that every approximately differentially private learning algorithm (possibly improper) for a class $H$ with Littlestone dimension~$d$ requires $\Omega\bigl(\log^*(d)\bigr)$ examples. As a corollary it follows that the class of…

Machine Learning · Computer Science 2019-03-11 Noga Alon , Roi Livni , Maryanthe Malliaris , Shay Moran

Verifying uniform conditions over continuous spaces through random sampling is fundamental in machine learning and control theory, yet classical coverage analyses often yield conservative bounds, particularly at small failure probabilities.…

Machine Learning · Computer Science 2025-12-15 Lyu Yuhuan

We investigate the direct-sum problem in the context of differentially private PAC learning: What is the sample complexity of solving $k$ learning tasks simultaneously under differential privacy, and how does this cost compare to that of…

Data Structures and Algorithms · Computer Science 2015-11-30 Mark Bun , Kobbi Nissim , Uri Stemmer

Understanding the relationship between generalization and privacy remains a central challenge in modern machine learning theory, particularly for deep networks trained by variants of differentially private stochastic gradient descent…

Machine Learning · Computer Science 2026-05-27 Christoph H. Lampert , Hossein Zakerinia

We study differentially private distributed optimization under communication constraints. A server using SGD for optimization aggregates the client-side local gradients for model updates using distributed mean estimation (DME). We develop a…

Machine Learning · Computer Science 2023-02-23 Antonious M. Girgis , Suhas Diggavi

A private learner is an algorithm that given a sample of labeled individual examples outputs a generalizing hypothesis while preserving the privacy of each individual. In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction…

Machine Learning · Computer Science 2015-07-03 Amos Beimel , Kobbi Nissim , Uri Stemmer

We revisit Wald's celebrated Sequential Probability Ratio Test for sequential tests of two simple hypotheses, under privacy constraints. We propose DP-SPRT, a wrapper that can be calibrated to achieve desired error probabilities and privacy…

Machine Learning · Statistics 2026-02-05 Thomas Michel , Debabrota Basu , Emilie Kaufmann

We consider a problem where multiple agents must learn an action profile that maximises the sum of their utilities in a distributed manner. The agents are assumed to have no knowledge of either the utility functions or the actions and…

Systems and Control · Computer Science 2016-03-31 Chithrupa Ramesh , Marius Schmitt , John Lygeros

Stability is a central property in learning and statistics promising the output of an algorithm $A$ does not change substantially when applied to similar datasets $S$ and $S'$. It is an elementary fact that any sufficiently stable algorithm…

Machine Learning · Computer Science 2025-02-13 Max Hopkins , Shay Moran

We introduce a new sample complexity measure, which we refer to as split-sample growth rate. For any hypothesis $H$ and for any sample $S$ of size $m$, the split-sample growth rate $\hat{\tau}_H(m)$ counts how many different hypotheses can…

Computer Science and Game Theory · Computer Science 2017-04-18 Vasilis Syrgkanis

Achieving differential privacy (DP) guarantees in fully decentralized machine learning is challenging due to the absence of a central aggregator and varying trust assumptions among nodes. We present a framework for DP analysis of…

Machine Learning · Computer Science 2026-02-06 Antti Koskela , Tejas Kulkarni

It is well known that estimating the expectation of any given bounded random variable with values in $[-B, B]$ has a sample complexity of $\mathrm{O}(B^2/\epsilon^2)$ that is independent of the underlying probability measure. We show that…

Optimization and Control · Mathematics 2026-04-29 Yan Li

We consider the problem of learning Markov Random Fields (including the prototypical example, the Ising model) under the constraint of differential privacy. Our learning goals include both structure learning, where we try to estimate the…

Data Structures and Algorithms · Computer Science 2020-08-17 Huanyu Zhang , Gautam Kamath , Janardhan Kulkarni , Zhiwei Steven Wu

We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss. Under modest assumptions on the input, we characterize the distribution of the iterate at each time…

Machine Learning · Computer Science 2024-02-22 Gavin Brown , Krishnamurthy Dvijotham , Georgina Evans , Daogao Liu , Adam Smith , Abhradeep Thakurta

We study the query complexity of Bayesian Private Learning: a learner wishes to locate a random target within an interval by submitting queries, in the presence of an adversary who observes all of her queries but not the responses. How many…

Machine Learning · Computer Science 2019-11-19 Kuang Xu

Suppose we are given access to $n$ independent samples from distribution $\mu$ and we wish to output one of them with the goal of making the output distributed as close as possible to a target distribution $\nu$. In this work we show that…

Machine Learning · Statistics 2024-02-27 Adam Block , Yury Polyanskiy

We study the sample complexity of private synthetic data generation over an unbounded sized class of statistical queries, and show that any class that is privately proper PAC learnable admits a private synthetic data generator (perhaps…

Machine Learning · Computer Science 2020-12-08 Olivier Bousquet , Roi Livni , Shay Moran

We study the problem of multi-task learning under user-level differential privacy, in which $n$ users contribute data to $m$ tasks, each involving a subset of users. One important aspect of the problem, that can significantly impact…

Machine Learning · Computer Science 2023-02-17 Walid Krichene , Prateek Jain , Shuang Song , Mukund Sundararajan , Abhradeep Thakurta , Li Zhang

This paper proves the tight sample complexity of {\sf Second-Price Auction with Anonymous Reserve}, up to a logarithmic factor, for each of all the value distribution families studied in the literature: $[0,\, 1]$-bounded, $[1,\,…

Computer Science and Game Theory · Computer Science 2022-11-04 Yaonan Jin , Pinyan Lu , Tao Xiao

Distributionally Robust Reinforcement Learning (DR-RL) aims to derive a policy optimizing the worst-case performance within a predefined uncertainty set. Despite extensive research, previous DR-RL algorithms have predominantly favored…

Machine Learning · Computer Science 2024-06-26 Yudan Wang , Shaofeng Zou , Yue Wang
‹ Prev 1 8 9 10 Next ›