Zobrazeno 1 - 10
of 203
pro vyhledávání: '"Schulman, Leonard J."'
We consider the dynamics imposed by natural selection on the populations of two competing, sexually reproducing, haploid species. In this setting, the fitness of any genome varies over time due to the changing population mix of the competing species;
Externí odkaz:
http://arxiv.org/abs/2406.03938
Product of experts (PoE) are layered networks in which the value at each node is an AND (or product) of the values (possibly negated) at its inputs. These were introduced as a neural network architecture that can efficiently learn to generate high-di
Externí odkaz:
http://arxiv.org/abs/2310.09397
We consider the problem of identifying, from statistics, a distribution of discrete random variables $X_1,\ldots,X_n$ that is a mixture of $k$ product distributions. The best previous sample complexity for $n \in O(k)$ was $(1/\zeta)^{O(k^2 \log k)}$
Externí odkaz:
http://arxiv.org/abs/2309.13993
Publikováno v:
Proceedings of Machine Learning Research vol 213:1-27, 2023
A Bayesian Network is a directed acyclic graph (DAG) on a set of $n$ random variables (the vertices); a Bayesian Network Distribution (BND) is a probability distribution on the random variables that is Markovian on the graph. A finite $k$-mixture of
Externí odkaz:
http://arxiv.org/abs/2112.11602
In the Euclidean $k$-Means problem we are given a collection of $n$ points $D$ in an Euclidean space and a positive integer $k$. Our goal is to identify a collection of $k$ points in the same space (centers) so as to minimize the sum of the squared E
Externí odkaz:
http://arxiv.org/abs/2107.07358
The Hadamard Extension of a matrix is the matrix consisting of all Hadamard products of subsets of its rows. This construction arises in the context of identifying a mixture of product distributions on binary random variables: full column rank of suc
Externí odkaz:
http://arxiv.org/abs/2101.11688
We give an algorithm for source identification of a mixture of $k$ product distributions on $n$ bits. This is a fundamental problem in machine learning with many applications. Our algorithm identifies the source parameters of an identifiable mixture,
Externí odkaz:
http://arxiv.org/abs/2012.14540
We consider the problem of identifying, from its first $m$ noisy moments, a probability distribution on $[0,1]$ of support $k<\infty$. This is equivalent to the problem of learning a distribution on $m$ observable binary random variables $X_1,X_2,\do
Externí odkaz:
http://arxiv.org/abs/2007.08101
Autor:
Mehta, Jenish C., Schulman, Leonard J.
The classic graphical Cheeger inequalities state that if $M$ is an $n\times n$ symmetric doubly stochastic matrix, then \[ \frac{1-\lambda_{2}(M)}{2}\leq\phi(M)\leq\sqrt{2\cdot(1-\lambda_{2}(M))} \] where $\phi(M)=\min_{S\subseteq[n],|S|\leq n/2}\lef
Externí odkaz:
http://arxiv.org/abs/1909.12497
Autor:
Kalai, Gil, Schulman, Leonard J.
Publikováno v:
Israel J. Math., 2019
We consider multilinear Littlewood polynomials, polynomials in $n$ variables in which a specified set of monomials $U$ have $\pm 1$ coefficients, and all other coefficients are $0$. We provide upper and lower bounds (which are close for $U$ of degree
Externí odkaz:
http://arxiv.org/abs/1804.04828