Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 5
Divide and Conquer Kernel Ridge Regression
Yuchen Zhang
Video in druga učna gradiva
Oznake: computer science;machine learning
We study a decomposition-based scalable approach to performing kernel ridge regression. The method is simply described: it randomly partitions a dataset of size N into m subsets of equal size, computes an independent kernel ridge regression estimator for each subset, then averages the local solution ...
Leto: 2013 Vir: videolectures.net
Lower bounds on the performance of polynomial-time algorithms for sparse linear regression
Yuchen Zhang
Video in druga učna gradiva
Oznake: computer science;machine learning;computational learning theory;statistical learning;unsupervised learning;supervised learning;on-line learning
Under a standard assumption in complexity theory (NP not in P/poly), we demonstrate a gap between the minimax prediction risk for sparse linear regression that can be achieved by polynomial-time algorithms, and that achieved by optimal algorithms. In particular, when the design matrix is ill-conditi ...
Leto: 2014 Vir: videolectures.net
Distributed Estimation of Generalized Matrix Rank: Efficient Algorithms and Lower Bounds
Yuchen Zhang
Video in druga učna gradiva
Oznake: computer science;machine learning
We study the following generalized matrix rank estimation problem: given an n-by-n matrix and a constant c>0, estimate the number of eigenvalues that are greater than c. In the distributed setting, the matrix of interest is the sum of m matrices held by separate machines. We show that any determinis ...
Leto: 2015 Vir: videolectures.net
DiSCO: Distributed Optimization for Self-Concordant Empirical Loss
Yuchen Zhang
Video in druga učna gradiva
Oznake: computer science;machine learning
We propose a new distributed algorithm for empirical risk minimization in machine learning. The algorithm is based on an inexact damped Newton method, where the inexact Newton steps are computed by a distributed preconditioned conjugate gradient method. We analyze its iteration complexity and commun ...
Leto: 2015 Vir: videolectures.net
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
Yuchen Zhang
Video in druga učna gradiva
Oznake: computer science;machine learning
We consider a generic convex optimization problem associated with regularized empirical risk minimization of linear predictors. The problem structure allows us to reformulate it as a convex-concave saddle point problem. We propose a stochastic primal-dual coordinate method, which alternates between ...
Leto: 2015 Vir: videolectures.net
Št. zadetkov: 5
Ključne besede:
Leto izdaje:
Repozitorij:
Tipologija:
Jezik: