G
Gregory Valiant
Researcher at Stanford University
Publications - 145
Citations - 5380
Gregory Valiant is an academic researcher from Stanford University. The author has contributed to research in topics: Estimator & Population. The author has an hindex of 37, co-authored 137 publications receiving 4607 citations. Previous affiliations of Gregory Valiant include University of California, Berkeley & Harvard University.
Papers
More filters
Proceedings ArticleDOI
Estimating the unseen: an n/log(n)-sample estimator for entropy and support size, shown optimal via new CLTs
Gregory Valiant,Paul Valiant +1 more
TL;DR: A new approach to characterizing the unobserved portion of a distribution is introduced, which provides sublinear--sample estimators achieving arbitrarily small additive constant error for a class of properties that includes entropy and distribution support size.
Posted Content
Settling the Polynomial Learnability of Mixtures of Gaussians
Ankur Moitra,Gregory Valiant +1 more
TL;DR: In this article, an efficient algorithm for learning univariate mixtures of two Gaussians was proposed, which has a running time polynomial in the dimension and the inverse of the desired accuracy, with provably minimal assumptions on the Gaussian parameters.
Proceedings ArticleDOI
Learning from untrusted data
TL;DR: In this paper, the authors consider two frameworks for studying estimation, learning, and optimization in the presence of significant fractions of arbitrary data, and provide an algorithm for robust learning in a very general stochastic optimization setting.
Proceedings ArticleDOI
Settling the Polynomial Learnability of Mixtures of Gaussians
Ankur Moitra,Gregory Valiant +1 more
TL;DR: This paper gives the first polynomial time algorithm for proper density estimation for mixtures of k Gaussians that needs no assumptions on the mixture, and proves that such a dependence is necessary.
Proceedings ArticleDOI
Efficiently learning mixtures of two Gaussians
TL;DR: This work provides a polynomial-time algorithm for this problem for the case of two Gaussians in $n$ dimensions (even if they overlap), with provably minimal assumptions on theGaussians, and polynometric data requirements, and efficiently performs near-optimal clustering.