11 citations · 15 across the 8 of their papers we have counts for
8 papers
Population Control meets Doob's Martingale Theorems: the Noise-free Multimodal Case
Marie-Liesse Cauwet, Olivier Teytaud
We study a test-based population size adaptation (TBPSA) method, inspired from population control, in the noise-free multimodal case. In the noisy setting, TBPSA usually recommends…
Fully Parallel Hyperparameter Search: Reshaped Space-Filling
M. -L. Cauwet, C. Couprie, J. Dehos +5
Space-filling designs such as scrambled-Hammersley, Latin Hypercube Sampling and Jittered Sampling have been proposed for fully parallel hyperparameter search, and were shown to be…
Surprising strategies obtained by stochastic optimization in partially observable games
Marie-Liesse Cauwet, Olivier Teytaud
This paper studies the optimization of strategies in the context of possibly randomized two players zero-sum games with incomplete information. We compare 5 algorithms for tuning t…
Analysis of Different Types of Regret in Continuous Noisy Optimization
Sandra Astete-Morales, Marie-Liesse Cauwet, Olivier Teytaud
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 i…
Noisy Optimization: Fast Convergence Rates with Comparison-Based Algorithms
Marie-Liesse Cauwet, Olivier Teytaud
Derivative Free Optimization is known to be an efficient and robust method to tackle the black-box optimization problem. When it comes to noisy functions, classical comparison-base…
Depth, balancing, and limits of the Elo model
Marie-Liesse Cauwet, Olivier Teytaud, Hua-Min Liang +5
-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-cent…
Algorithm Portfolios for Noisy Optimization
Marie-Liesse Cauwet, Jialin Liu, Rozière Baptiste +1
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 distribut…
Noisy Optimization: Convergence with a Fixed Number of Resamplings
Marie-Liesse Cauwet
It is known that evolution strategies in continuous domains might not converge in the presence of noise. It is also known that, under mild assumptions, and using an increasing numb…