Efficient learning of simplices
Authors:
- Joseph AndersonJAJoseph Anderson
- Navin GoyalNGNavin Goyal
- Luis RademacherLRLuis Rademacher
Preprint
Abstract
We show an efficient algorithm for the following problem: Given uniformly random points from an arbitrary n-dimensional simplex, estimate the simplex. The size of the sample and the number of arithmetic operations of our algorithm are polynomial in n. This answers a question of Frieze, Jerrum and Kannan [FJK]. Our result can also be interpreted as efficiently learning the intersection of n+1 half-spaces in R^n in the model where the intersection is bounded and we are given polynomially many uniform samples from it. Our proof uses the local search technique from Independent Component Analysis (ICA), also used by [FJK]. Unlike these previous algorithms, which were based on analyzing the fourth moment, ours is based on the third moment. We also show a direct connection between the problem of learning a simplex and ICA: a simple randomized reduction to ICA from the problem of learning a simplex. The connection is based on a known representation of the uniform measure on a simplex. Similar representations lead to a reduction from the problem of learning an affine transformation of an n-dimensional l_p ball to ICA.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Provable ICA with Unknown Gaussian Noise, and Implications for Gaussian Mixtures and AutoencodersAlgorithmica, 2015
- A random-sampling-based algorithm for learning intersections of halfspacesJournal of the ACM, 2010
- Learning Convex Concepts from Gaussian Distributions with PCA2010
- Quantitative estimates of the convergence of the empirical covariance matrix in log-concave ensemblesJournal of the American Mathematical Society, 2009
- Cryptographic hardness for learning intersections of halfspacesJournal of Computer and System Sciences, 2009
- A Lower Bound for Agnostically Learning Disjunctions2007
- Learning linear transformations2002
- Fast and robust fixed-point algorithms for independent component analysisIEEE Transactions on Neural Networks, 1999
- 𝐿_{𝑝}-norm uniform distributionProceedings of the American Mathematical Society, 1997
- Independent component analysis, A new concept?Signal Processing, 1994