Regret analysis of stochastic and nonstochastic multi-armed bandit problems
S Bubeck, N Cesa-Bianchi - Foundations and Trends® in …, 2012 - nowpublishers.com
Multi-armed bandit problems are the most basic examples of sequential decision problems
with an exploration-exploitation trade-off. This is the balance between staying with the option …
with an exploration-exploitation trade-off. This is the balance between staying with the option …
Stochastic first-and zeroth-order methods for nonconvex stochastic programming
In this paper, we introduce a new stochastic approximation type algorithm, namely, the
randomized stochastic gradient (RSG) method, for solving an important class of nonlinear …
randomized stochastic gradient (RSG) method, for solving an important class of nonlinear …
Robust stochastic approximation approach to stochastic programming
In this paper we consider optimization problems where the objective function is given in a
form of the expectation. A basic difficulty of solving such stochastic optimization problems is …
form of the expectation. A basic difficulty of solving such stochastic optimization problems is …
Dual averaging method for regularized stochastic learning and online optimization
L Xiao - Advances in Neural Information Processing …, 2009 - proceedings.neurips.cc
We consider regularized stochastic learning and online optimization problems, where the
objective function is the sum of two convex terms: one is the loss function of the learning …
objective function is the sum of two convex terms: one is the loss function of the learning …
An optimal method for stochastic composite optimization
G Lan - Mathematical Programming, 2012 - Springer
This paper considers an important class of convex programming (CP) problems, namely, the
stochastic composite optimization (SCO), whose objective function is given by the …
stochastic composite optimization (SCO), whose objective function is given by the …
Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization i: A generic algorithmic framework
In this paper we present a generic algorithmic framework, namely, the accelerated stochastic
approximation (AC-SA) algorithm, for solving strongly convex stochastic composite …
approximation (AC-SA) algorithm, for solving strongly convex stochastic composite …
Stochastic quasi-Newton methods for nonconvex stochastic optimization
In this paper we study stochastic quasi-Newton methods for nonconvex stochastic
optimization, where we assume that noisy information about the gradients of the objective …
optimization, where we assume that noisy information about the gradients of the objective …
Aggregation for Gaussian regression
F Bunea, AB Tsybakov, MH Wegkamp - 2007 - projecteuclid.org
This paper studies statistical aggregation procedures in the regression setting. A motivating
factor is the existence of many different methods of estimation, leading to possibly competing …
factor is the existence of many different methods of estimation, leading to possibly competing …
Regularization in statistics
This paper is a selective review of the regularization methods scattered in statistics literature.
We introduce a general conceptual approach to regularization and fit most existing methods …
We introduce a general conceptual approach to regularization and fit most existing methods …
Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity
A Dalalyan, AB Tsybakov - Machine Learning, 2008 - Springer
We study the problem of aggregation under the squared loss in the model of regression with
deterministic design. We obtain sharp PAC-Bayesian risk bounds for aggregates defined via …
deterministic design. We obtain sharp PAC-Bayesian risk bounds for aggregates defined via …