Jun 6, 2017 · We consider PAC learning of probability distributions (aka density estimation), where we are given an iid sample generated from an unknown target distribution.
scholar.google.com › citations
Apr 29, 2018 · We consider PAC learning of probability distributions (a.k.a. density estimation), where we are given an i.i.d. sample generated from an unknown ...
In this paper, we assume that the algorithm knows the number of components k. As a demonstration, we show that our method provides a better sample complexity ...
The paper studies the problem of learning a mixture of k d -dimensional Gaussians using a differentially private mechanism with respect to the samples. It ...
Jun 6, 2017 · Our mixture learning algorithm has the property that, if the F -learner is proper/agnostic, then the F k -learner would be proper/agnostic as ...
Spotlight Poster. Sample-Efficient Private Learning of Mixtures of Gaussians. Hassan Ashtiani · Mahbod Majid · Shyam Narayanan. West Ballroom A-D #6202.
In this work, we study the problem of learning a GMM from samples. We focus on the density estimation setting, where the goal is to learn the overall mixture ...
People also ask
What is sample efficiency in deep learning?
What are the kinds of mixtures you have learned?
Nov 4, 2024 · In this work, we study the problem of learning a GMM from samples. We focus on the density estimation setting, where the goal is to learn the ...
We introduce a novel technique for distribution learning based on a notion of sample compression . Any class of distributions that allows such a compression ...
We propose a learning algorithm that accurately recovers the underlying matrix using 9(M) number of samples, which immediately lead to improved learning ...