English
Related papers

Related papers: Agnostic Private Density Estimation for GMMs via L…

200 papers

We provide sample complexity upper bounds for agnostically learning multivariate Gaussians under the constraint of approximate differential privacy. These are the first finite sample upper bounds for general Gaussians which do not impose…

Machine Learning · Statistics 2020-10-21 Ishaq Aden-Ali , Hassan Ashtiani , Gautam Kamath

We study the problem of estimating mixtures of Gaussians under the constraint of differential privacy (DP). Our main result is that $\text{poly}(k,d,1/\alpha,1/\varepsilon,\log(1/\delta))$ samples are sufficient to estimate a mixture of $k$…

Machine Learning · Statistics 2024-04-24 Mohammad Afzali , Hassan Ashtiani , Christopher Liaw

Two seminal papers--Alon, Livni, Malliaris, Moran (STOC 2019) and Bun, Livni, and Moran (FOCS 2020)--established the equivalence between online learnability and globally stable PAC learnability in binary classification. However, Chase,…

Machine Learning · Computer Science 2025-05-19 Ari Blondal , Shan Gao , Hamed Hatami , Pooya Hatami

We study the problem of privately estimating the parameters of $d$-dimensional Gaussian Mixture Models (GMMs) with $k$ components. For this, we develop a technique to reduce the problem to its non-private counterpart. This allows us to…

Machine Learning · Statistics 2023-06-09 Jamil Arbas , Hassan Ashtiani , Christopher Liaw

We design differentially private learning algorithms that are agnostic to the learning model. Our algorithms are interactive in nature, i.e., instead of outputting a model based on the training data, they provide predictions for a set of…

Machine Learning · Computer Science 2018-03-15 Raef Bassily , Om Thakkar , Abhradeep Thakurta

This work represents a natural coalescence of two important lines of work: learning mixtures of Gaussians and algorithmic robust statistics. In particular we give the first provably robust algorithm for learning mixtures of any constant…

Data Structures and Algorithms · Computer Science 2021-07-27 Allen Liu , Ankur Moitra

Estimation of structure, such as in variable selection, graphical modelling or cluster analysis is notoriously difficult, especially for high-dimensional data. We introduce stability selection. It is based on subsampling in combination with…

Methodology · Statistics 2009-05-16 Nicolai Meinshausen , Peter Buehlmann

We study the task of learning Generalized Linear models (GLMs) in the agnostic model under the Gaussian distribution. We give the first polynomial-time algorithm that achieves a constant-factor approximation for \textit{any} monotone…

Machine Learning · Computer Science 2025-08-05 Nikos Zarifis , Puqian Wang , Ilias Diakonikolas , Jelena Diakonikolas

Inspired by the problem of improving classification accuracy on rare or hard subsets of a population, there has been recent interest in models of learning where the goal is to generalize to a collection of distributions, each representing a…

Machine Learning · Computer Science 2023-06-06 Nick Rittler , Kamalika Chaudhuri

We consider the problem of learning mixtures of Gaussians under the constraint of approximate differential privacy. We prove that $\widetilde{O}(k^2 d \log^{3/2}(1/\delta) / \alpha^2 \varepsilon)$ samples are sufficient to learn a mixture…

Machine Learning · Computer Science 2021-06-07 Ishaq Aden-Ali , Hassan Ashtiani , Christopher Liaw

We study the problem of agnostic learning under the Gaussian distribution. We develop a method for finding hard families of examples for a wide class of problems by using LP duality. For Boolean-valued concept classes, we show that the…

Machine Learning · Computer Science 2021-02-09 Ilias Diakonikolas , Daniel M. Kane , Thanasis Pittas , Nikos Zarifis

We present a new subspace-based method to construct probabilistic models for high-dimensional data and highlight its use in anomaly detection. The approach is based on a statistical estimation of probability density using densities of…

Machine Learning · Computer Science 2021-08-16 Cetin Savkli , Catherine Schwartz

Deep Markov models (DMM) are generative models that are scalable and expressive generalization of Markov models for representation, learning, and inference problems. However, the fundamental stochastic stability guarantees of such models…

Machine Learning · Computer Science 2021-11-09 Ján Drgoňa , Sayak Mukherjee , Jiaxin Zhang , Frank Liu , Mahantesh Halappanavar

This paper proposes a novel method for testing observability in Gaussian models using discrete density approximations (deterministic samples) of (multivariate) Gaussians. Our notion of observability is defined by the existence of the…

Systems and Control · Electrical Eng. & Systems 2022-08-19 Ariane Hanebeck , Claudia Czado

Generative Adversarial Networks (GANs) have become a popular method to learn a probability model from data. In this paper, we aim to provide an understanding of some of the basic issues surrounding GANs including their formulation,…

Machine Learning · Statistics 2018-10-23 Soheil Feizi , Farzan Farnia , Tony Ginart , David Tse

In this work we solve the problem of robustly learning a high-dimensional Gaussian mixture model with $k$ components from $\epsilon$-corrupted samples up to accuracy $\widetilde{O}(\epsilon)$ in total variation distance for any constant $k$…

Machine Learning · Computer Science 2021-11-16 Allen Liu , Ankur Moitra

We study the problem of agnostically learning halfspaces under the Gaussian distribution. Our main result is the {\em first proper} learning algorithm for this problem whose sample complexity and computational complexity qualitatively match…

Machine Learning · Computer Science 2021-02-11 Ilias Diakonikolas , Daniel M. Kane , Vasilis Kontonis , Christos Tzamos , Nikos Zarifis

We study the problem of private distribution learning with access to public data. In this setup, which we refer to as public-private learning, the learner is given public and private samples drawn from an unknown distribution $p$ belonging…

Machine Learning · Computer Science 2023-08-16 Shai Ben-David , Alex Bie , Clément L. Canonne , Gautam Kamath , Vikrant Singhal

It has long been thought that high-dimensional data encountered in many practical machine learning tasks have low-dimensional structure, i.e., the manifold hypothesis holds. A natural question, thus, is to estimate the intrinsic dimension…

Machine Learning · Statistics 2022-06-01 Adam Block , Zeyu Jia , Yury Polyanskiy , Alexander Rakhlin

In high-dimensional graph learning problems, some topological properties of the graph, such as bounded node degree or tree structure, are typically assumed to hold so that the sample complexity of recovering the graph structure can be…

Statistics Theory · Mathematics 2018-06-12 De Wen Soh , Sekhar Tatikonda
‹ Prev 1 2 3 10 Next ›