English
Related papers

Related papers: Sample-Efficient Learning of Mixtures

200 papers

We study the problem of {\em distribution-independent} PAC learning of halfspaces in the presence of Massart noise. Specifically, we are given a set of labeled examples $(\mathbf{x}, y)$ drawn from a distribution $\mathcal{D}$ on…

Machine Learning · Computer Science 2019-12-11 Ilias Diakonikolas , Themis Gouleakis , Christos Tzamos

Gaussian Processes (GPs) are a generic modelling tool for supervised learning. While they have been successfully applied on large datasets, their use in safety-critical applications is hindered by the lack of good performance guarantees. To…

Machine Learning · Statistics 2019-08-27 David Reeb , Andreas Doerr , Sebastian Gerwinn , Barbara Rakitsch

We resolve one of the major outstanding problems in robust statistics. In particular, if $X$ is an evenly weighted mixture of two arbitrary $d$-dimensional Gaussians, we devise a polynomial time algorithm that given access to samples from…

Data Structures and Algorithms · Computer Science 2020-07-14 Daniel M. Kane

Recently developed techniques have made it possible to quickly learn accurate probability density functions from data in low-dimensional continuous space. In particular, mixtures of Gaussians can be fitted to data very quickly using an…

Machine Learning · Computer Science 2013-01-18 Scott Davies , Andrew Moore

We study distribution-free property testing and learning problems where the unknown probability distribution is a product distribution over $\mathbb{R}^d$. For many important classes of functions, such as intersections of halfspaces,…

Data Structures and Algorithms · Computer Science 2021-11-17 Nathaniel Harms , Yuichi Yoshida

This work establishes a new upper bound on the number of samples sufficient for PAC learning in the realizable case. The bound matches known lower bounds up to numerical constant factors. This solves a long-standing open problem on the…

Machine Learning · Computer Science 2016-09-13 Steve Hanneke

We study the problem of learning a mixture model of non-parametric product distributions. The problem of learning a mixture model is that of finding the component distributions along with the mixing weights using observed samples generated…

Signal Processing · Electrical Eng. & Systems 2019-04-03 Nikos Kargas , Nicholas D. Sidiropoulos

We study the complexity of learning $k$-mixtures of Gaussians ($k$-GMMs) on $\mathbb{R}^d$. This task is known to have complexity $d^{\Omega(k)}$ in full generality. To circumvent this exponential lower bound on the number of components,…

Machine Learning · Computer Science 2025-04-22 Ilias Diakonikolas , Daniel M. Kane , Sushrut Karmalkar , Jasper C. H. Lee , Thanasis Pittas

We develop a theory of high-arity PAC learning, which is statistical learning in the presence of "structured correlation". In this theory, hypotheses are either graphs, hypergraphs or, more generally, structures in finite relational…

Machine Learning · Computer Science 2024-09-18 Leonardo N. Coregliano , Maryanthe Malliaris

We introduce a new model of membership query (MQ) learning, where the learning algorithm is restricted to query points that are \emph{close} to random examples drawn from the underlying distribution. The learning model is intermediate…

Machine Learning · Computer Science 2013-04-19 Pranjal Awasthi , Vitaly Feldman , Varun Kanade

Machine Learning (ML) models in Robotic Assembly Sequence Planning (RASP) need to be introspective on the predicted solutions, i.e. whether they are feasible or not, to circumvent potential efficiency degradation. Previous works need both…

We investigate the computational efficiency of agnostic learning for several fundamental geometric concept classes in the plane. While the sample complexity of agnostic learning is well understood, its time complexity has received much less…

Data Structures and Algorithms · Computer Science 2025-10-22 Talya Eden , Ludmila Glinskih , Sofya Raskhodnikova

How quickly can a given class of concepts be learned from examples? It is common to measure the performance of a supervised machine learning algorithm by plotting its "learning curve", that is, the decay of the error rate as a function of…

Machine Learning · Computer Science 2020-11-10 Olivier Bousquet , Steve Hanneke , Shay Moran , Ramon van Handel , Amir Yehudayoff

Learning from label proportions (LLP) is a generalization of supervised learning in which the training data is available as sets or bags of feature-vectors (instances) along with the average instance-label of each bag. The goal is to train…

Machine Learning · Computer Science 2023-10-17 Anand Brahmbhatt , Rishi Saket , Aravindan Raghuveer

Several well-studied models of access to data samples, including statistical queries, local differential privacy and low-communication algorithms rely on queries that provide information about a function of a single sample. (For example, a…

Machine Learning · Computer Science 2017-03-02 Vitaly Feldman , Badih Ghazi

The apparent difficulty of efficient distribution-free PAC learning has led to a large body of work on distribution-specific learning. Distributional assumptions facilitate the design of efficient algorithms but also limit their reach and…

Machine Learning · Computer Science 2025-06-23 Guy Blanc , Jane Lange , Carmen Strassle , Li-Yang Tan

Probabilistic clustering models (or equivalently, mixture models) are basic building blocks in countless statistical models and involve latent random variables over discrete spaces. For these models, posterior inference methods can be…

Machine Learning · Statistics 2020-06-24 Ari Pakman , Yueqi Wang , Catalin Mitelut , JinHyung Lee , Liam Paninski

We study the power of query access for the task of agnostic learning under the Gaussian distribution. In the agnostic model, no assumptions are made on the labels and the goal is to compute a hypothesis that is competitive with the {\em…

Machine Learning · Computer Science 2023-12-29 Ilias Diakonikolas , Daniel M. Kane , Vasilis Kontonis , Christos Tzamos , Nikos Zarifis

We use the Sum of Squares method to develop new efficient algorithms for learning well-separated mixtures of Gaussians and robust mean estimation, both in high dimensions, that substantially improve upon the statistical guarantees achieved…

Data Structures and Algorithms · Computer Science 2017-11-21 Samuel B. Hopkins , Jerry Li

Likelihood-free methods perform parameter inference in stochastic simulator models where evaluating the likelihood is intractable but sampling synthetic data is possible. One class of methods for this likelihood-free problem uses a…

Machine Learning · Statistics 2020-12-21 Conor Durkan , Iain Murray , George Papamakarios