#### Filter Results:

- Full text PDF available (10)

#### Publication Year

2014

2016

- This year (0)
- Last 5 years (11)
- Last 10 years (11)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

Learn More

We consider the problem of optimizing functions corrupted with additive noise. It is known that Evolutionary Algorithms can reach a Simple Regret <i>O</i>(1/√<i>n</i>) within logarithmic factors, when <i>n</i> is the number of function evaluations. Here, Simple Regret at evaluation $n$ is the difference between the evaluation of the function at the… (More)

- Marie-Liesse Cauwet, Jialin Liu, Baptiste Rozière, Olivier Teytaud
- Annals of Mathematics and Artificial Intelligence
- 2015

Noisy optimization is the optimization of objective functions corrupted by noise. A portfolio of solvers is a set of solvers equipped with an algorithm selection tool for distributing the computational power among them. Portfolios are widely and successfully used in combinatorial optimization. In this work, we study portfolios of noisy optimization solvers.… (More)

- Marie-Liesse Cauwet, Jialin Liu, Olivier Teytaud
- LION
- 2014

- Sandra Astete Morales, Marie-Liesse Cauwet, Jialin Liu, Olivier Teytaud
- Theor. Comput. Sci.
- 2016

Various papers have analyzed the noisy optimization of convex functions. This analysis has been made according to several criteria used to evaluate the performance of algorithms: uniform rate, simple regret and cumulative regret. We propose an iterative optimization framework, a particular instance of which, using Hessian approximations, provably (i)… (More)

- Marie-Liesse Cauwet
- EvoApplications
- 2014

It is known that evolution strategies in continuous domains might not converge in the presence of noise [3,14]. It is also known that, under mild assumptions, and using an increasing number of resamplings, one can mitigate the effect of additive noise [4] and recover convergence. We show new sufficient conditions for the convergence of an evolutionary… (More)

The performance measure of an algorithm is a crucial part of its analysis. The performance can be determined by the study on the convergence rate of the algorithm in question. It is necessary to study some (hopefully convergent) sequence that will measure how "good" is the approximated optimum compared to the real optimum. The concept of <i>Regret</i> is… (More)

- Marie-Liesse Cauwet, Olivier Teytaud
- PSCC
- 2016

The optimization of capacities in large scale power systems is a stochastic problem, because the need for storage and connections (i.e. exchange capacities) varies a lot from one week to another (e.g. power generation is subject to the vagaries of wind) and from one winter to another (e.g. water inflows due to snow melting). It is usually tackled through… (More)

- Marie-Liesse Cauwet, Olivier Teytaud, +4 authors Fabien Teytaud
- FOGA
- 2015

We study mathematically and experimentally the convergence rate of differential evolution and particle swarm optimization for simple unimodal functions. Due to parallelization concerns, the focus is on lower bounds on the runtime, i.e. upper bounds on the speed-up, as a function of the population size. Two cases are particularly relevant: A population size… (More)

- Marie-Liesse Cauwet, Olivier Teytaud, +5 authors Abdallah Saffidine
- 2015 IEEE Conference on Computational…
- 2015

Much work has been devoted to the computational complexity of games. However, they are not necessarily relevant for estimating the complexity in human terms. Therefore, human-centered measures have been proposed, e.g. the depth. This paper discusses the depth of various games, extends it to a continuous measure. We provide new depth results and present tool… (More)

In an optimization framework, some criteria might be more relevant than others; the internal computational cost of the optimization algorithm might be negligible or not; the quality of intermediate search points might be important or not. For this reason measuring the performance of an algorithm is a delicate task. In addition, the usual criteria are often… (More)