Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression

We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first algorithm that achieves jointly the optimal prediction error rates for least-squares regression, both in terms of forgetting the initial conditions in O (1 / n(2)), and in terms of dependence on the noise and dimension d of the problem, as O (d / n). Our new algorithm is based on averaged accelerated regularized gradient descent, and may also be analyzed through finer assumptions on initial conditions and the Hessian matrix, leading to dimension-free quantities that may still be small in some distances while the "optimal" terms above are large. In order to characterize the tightness of these new bounds, we consider an application to non-parametric regression and use the known lower bounds on the statistical performance (without computational limits), which happen to match our bounds obtained from a single pass on the data and thus show optimality of our algorithm in a wide variety of particular trade-offs between bias and variance.

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Concepts associés

Chargement

Publications associées

Chargement

Aymeric Daphnis Kévin Dieuleveut, Nicolas Henri Bernard Flammarion
2017
Article

Résumé

Official source

https://infoscience.epfl.ch/record/272845?ln=fr

À propos de ce résultat

Concepts associés (19)

Concepts associés

Chargement

Publications associées (9)

Publications associées

Chargement

Algorithme du gradient

Lalgorithme du gradient, aussi appelé algorithme de descente de gradient, désigne un algorithme d'optimisation différentiable. Il est par conséquent destiné à minimiser une fonction réelle différentia

Dimension

Le terme dimension, du latin dimensio « action de mesurer », désigne d’abord chacune des grandeurs d’un objet : longueur, largeur et profondeur, épaisseur ou hauteur, ou encore son diamètre si c'est

Fonction objectif

vignette|comparaison de certains substituts de la fonction de perte Le terme fonction objectif ou fonction économique, est utilisé en optimisation mathématique et en recherche opérationnelle pour dési

From averaging to acceleration, there is only a step-size

Nicolas Henri Bernard Flammarion

We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first algorithm that achieves jointly the optimal prediction error rates for least-squares regression, both in terms of forgetting of initial conditions in O(1/n 2), and in terms of dependence on the noise and dimension d of the problem, as O(d/n). Our new algorithm is based on averaged accelerated regularized gradient descent, and may also be analyzed through finer assumptions on initial conditions and the Hessian matrix, leading to dimension-free quantities that may still be small while the " optimal " terms above are large. In order to characterize the tightness of these new bounds, we consider an application to non-parametric regression and use the known lower bounds on the statistical performance (without computational limits), which happen to match our bounds obtained from a single pass on the data and thus show optimality of our algorithm in a wide variety of particular trade-offs between bias and variance.

2015

Chargement

Stochastic Zeroth-Order Optimisation Algorithms with Variance Reduction

Ahmad Ajalloeian

Introduction of optimisation problems in which the objective function is black box or obtaining the gradient is infeasible, has recently raised interest in zeroth-order optimisation methods. As an example finding adversarial examples for Deep Learning models (Chen et al. (2017); Moosavi-Dezfooli et al. (2016)) is one of the most common applications in which zeroth-order methods could be used. These optimisation methods use only function values at certain points to estimate the gradient. Most current approaches iteratively sample a random search direction along which they compute an estimation of the gradient (Nesterov and Spokoiny (2017); Conn et al. (2009); Wibisono et al. (2012)). However, due to the high variance in the search direction, these methods usually need d times more iterations than the standard gradient methods, where d is the dimensionality of the problem. So it seems that the main effort for improving the zeroth-order methods should be in reducing the variance of the gradient estimate. In this work we will analyse the gradient-free oracle which uses random directions sampled form a Gaussian distribution. Our analysis shows that in smooth and strongly convex setting, we have a convergence rate of O( d/T) which clearly shows the dependency to the dimension of the problem. Furthermore we propose some variance reduction methods to make the zeroth-order optimisation faster. We experiment our proposed methods in Python to compare their convergence in stochastic and non-stochastic setting. Our empirical results show that in a setting that number of allowed function evaluation is fixed, using a variance reduction method (e.g. momentum) can make the convergence of zeroth-order methods happen faster.

2019

Chargement

We describe the first gradient methods on Riemannian manifolds to achieve accelerated rates in the non-convex case. Under Lipschitz assumptions on the Riemannian gradient and Hessian of the cost function, these methods find approximate first-order critical points faster than regular gradient descent. A randomized version also finds approximate second-order critical points. Both the algorithms and their analyses build extensively on existing work in the Euclidean case. The basic operation consists in running the Euclidean accelerated gradient descent method (appropriately safe-guarded against non-convexity) in the current tangent space, then moving back to the manifold and repeating. This requires lifting the cost function from the manifold to the tangent space, which can be done for example through the Riemannian exponential map. For this approach to succeed, the lifted cost function (called the pullback) must retain certain Lipschitz properties. As a contribution of independent interest, we prove precise claims to that effect, with explicit constants. Those claims are affected by the Riemannian curvature of the manifold, which in turn affects the worst-case complexity bounds for our optimization algorithms.

SPRINGER2022

Chargement