Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 7
Message-passing for Graph-structured Linear Programs
Alekh Agarwal
Video in druga učna gradiva
Oznake: computer science;machine learning
Linear programming relaxations are one promising approach to solving the MAP estimation problem in Markov random fields; in particular, a body of past work has focused on the first-order tree-based LP relaxation for the MAP problem. Although a variety of algorithms with interesting connections to th ...
Leto: 2008 Vir: videolectures.net
Fast global convergence rates of gradient methods for high-dimensional statistical recovery
Alekh Agarwal
Video in druga učna gradiva
Oznake: computer science;machine learning;regression
Many statistical M-estimators are based on convex optimization problems formed by the weighted sum of a loss function with a norm-based regularizer. We analyze the convergence rates of first-order gradient methods for solving such problems within a high-dimensional framework that allows the data di ...
Leto: 2010 Vir: videolectures.net
Information-theoretic lower bounds on the oracle complexity of sparse convex optimization
Alekh Agarwal
Video in druga učna gradiva
Oznake: computer science;optimization methods
Relative to the large literature on upper bounds on complexity of convex optimization, lesser attention has been paid to the fundamental hardness of these problems. Recent years have seen a surge in optimization methods tailored to sparse optimization problems. In this paper, we study the complexity ...
Leto: 2010 Vir: videolectures.net
Stochastic optimization with non-i.id. noise
Alekh Agarwal
Video in druga učna gradiva
Oznake: computer science;optimization methods;stochastic optimization
We study the convergence of a class of stable online algorithms for stochastic convex optimization in settings where we do not receive independent samples from the distribution over which we optimize, but instead receive samples that are coupled over time. We show the optimization error of the avera ...
Leto: 2011 Vir: videolectures.net
Selective sampling algorithms for cost-sensitive multiclass prediction
Alekh Agarwal
Video in druga učna gradiva
Oznake: computer science;machine learning
In this talk, we study the problem of active learning for cost-sensitive multiclass classification. We propose selective sampling algorithms, which process the data in a streaming fashion, querying only a subset of the labels. For these algorithms, we analyze the regret and label complexity when the ...
Leto: 2013 Vir: videolectures.net
Oracle inequalities for computationally budgeted model selection
Alekh Agarwal
Video in druga učna gradiva
Oznake: science;complexity science
We analyze general model selection procedures using penalized empirical loss minimization under computational constraints. While classical model selection approaches do not consider computational aspects of performing model selection, we argue that any practical model selection procedure must not on ...
Leto: 2011 Vir: videolectures.net
A Lower Bound for the Optimization of Finite Sums
Alekh Agarwal
Video in druga učna gradiva
Oznake: computer science;machine learning
This paper presents a lower bound for optimizing a finite sum of n functions, where each function is L-smooth and the sum is μ-strongly convex. We show that no algorithm can reach an error ϵ in minimizing all functions from this class in fewer than Ω(n+n(κ−1)−−−−−−−√log(1/ϵ)) iterations, where κ=L/μ ...
Leto: 2015 Vir: videolectures.net
Št. zadetkov: 7
Ključne besede:
Leto izdaje:
Repozitorij:
Tipologija:
Jezik: