# LM-CMA: an Alternative to L-BFGS for Large Scale Black-box Optimization

1 Laboratory of Intelligent Systems (LIS)
LIS - Laboratory of Intelligent Systems
Abstract : The limited memory BFGS method (L-BFGS) of Liu and Nocedal (1989) is often considered to be the method of choice for continuous optimization when first- and/or second- order information is available. However, the use of L-BFGS can be complicated in a black-box scenario where gradient information is not available and therefore should be numerically estimated. The accuracy of this estimation, obtained by finite difference methods, is often problem-dependent that may lead to premature convergence of the algorithm. In this paper, we demonstrate an alternative to L-BFGS, the limited memory Covariance Matrix Adaptation Evolution Strategy (LM-CMA) proposed by Loshchilov (2014). The LM-CMA is a stochastic derivative-free algorithm for numerical optimization of non-linear, non-convex optimization problems. Inspired by the L-BFGS, the LM-CMA samples candidate solutions according to a covariance matrix reproduced from $m$ direction vectors selected during the optimization process. The decomposition of the covariance matrix into Cholesky factors allows to reduce the memory complexity to $O(mn)$, where $n$ is the number of decision variables. The time complexity of sampling one candidate solution is also $O(mn)$, but scales as only about 25 scalar-vector multiplications in practice. The algorithm has an important property of invariance w.r.t. strictly increasing transformations of the objective function, such transformations do not compromise its ability to approach the optimum. The LM-CMA outperforms the original CMA-ES and its large scale versions on non-separable ill-conditioned problems with a factor increasing with problem dimension. Invariance properties of the algorithm do not prevent it from demonstrating a comparable performance to L-BFGS on non-trivial large scale smooth and nonsmooth optimization problems.
Keywords :
Type de document :
Article dans une revue
Evolutionary Computation, Massachusetts Institute of Technology Press (MIT Press), 2015
Domaine :

Littérature citée [56 références]

https://hal.inria.fr/hal-01218646
Contributeur : Loshchilov Ilya <>
Soumis le : mercredi 21 octobre 2015 - 15:06:15
Dernière modification le : lundi 21 mars 2016 - 17:34:19
Document(s) archivé(s) le : samedi 23 janvier 2016 - 00:36:58

### Fichiers

LMCMA_ECJ2015.pdf
Fichiers produits par l'(les) auteur(s)

### Identifiants

• HAL Id : hal-01218646, version 1

### Citation

Ilya Loshchilov. LM-CMA: an Alternative to L-BFGS for Large Scale Black-box Optimization. Evolutionary Computation, Massachusetts Institute of Technology Press (MIT Press), 2015. 〈hal-01218646〉

### Métriques

Consultations de la notice

## 75

Téléchargements de fichiers