Versatile black-box optimization

Liu, Jialin; Moreau, Antoine; Preuß, Mike; Rapin, Jérémy; Rozière, Baptiste; Teytaud, Fabien; Teytaud, Olivier

doi:10.1145/3377930.3389838

Cited by 20 publications

(17 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current focus of Nevergrad is to be seen on the problem side, as it ofers several new benchmark problems, such as the structured optimization problems which are aggregated in their own test suite. Nevergrad also provides interfaces to the following benchmark collections: LSGO [45], YABBOB [46], Pyomo [32], MLDA [24], and MuJoCo [56]. The performance evaluation, however, is much more basic than those of COCO or IOHanalyzer, in that only the quality of the inally recommended point(s) is stored, but no information about the search trajectory.…”

Section: Related Benchmarking Environmentsmentioning

confidence: 99%

IOHanalyzer: Detailed Performance Analyses for Iterative Optimization Heuristics

Wang

Vermetten

et al. 2022

ACM Trans. Evol. Learn. Optim.

View full text Add to dashboard Cite

Benchmarking and performance analysis play an important role in understanding the behaviour of iterative optimization heuristics (IOHs) such as local search algorithms, genetic and evolutionary algorithms, Bayesian optimization algorithms, etc. This task, however, involves manual setup, execution, and analysis of the experiment on an individual basis, which is laborious and can be mitigated by a generic and well-designed platform. For this purpose, we propose IOHanalyzer, a new user-friendly tool for the analysis, comparison, and visualization of performance data of IOHs. Implemented in R and C++ , IOHanalyzer is fully open source. It is available on CRAN and GitHub. IOHanalyzer provides detailed statistics about fixed-target running times and about fixed-budget performance of the benchmarked algorithms with a real-valued codomain, single-objective optimization tasks. Performance aggregation over several benchmark problems is possible, for example in the form of empirical cumulative distribution functions. Key advantages of IOHanalyzer over other performance analysis packages are its highly interactive design, which allows users to specify the performance measures, ranges, and granularity that are most useful for their experiments, and the possibility to analyze not only performance traces, but also the evolution of dynamic state parameters. IOHanalyzer can directly process performance data from the main benchmarking platforms, including the COCO platform, Nevergrad, the SOS platform, and IOHexperimenter. An R programming interface is provided for users preferring to have a finer control over the implemented functionalities.

show abstract

Section: Related Benchmarking Environmentsmentioning

confidence: 99%

IOHanalyzer: Detailed Performance Analyses for Iterative Optimization Heuristics

Wang

Vermetten

et al. 2022

ACM Trans. Evol. Learn. Optim.

View full text Add to dashboard Cite

show abstract

“…TBPSA is a specific implementation of pcCMAES [36], a variant of CMAES. It evaluates points with a strong mutation rate and performs small steps in the best direction, relying on the longer-range trends of the objective landscape [37].…”

Section: Evolution Strategy and Bayesian Optimisationmentioning

confidence: 99%

Multi-Modal Legged Locomotion Framework with Automated Residual Reinforcement Learning

Chen¹,

Rosendo²

2022

Preprint

View full text Add to dashboard Cite

While quadruped robots usually have good stability and load capacity, bipedal robots offer a higher level of flexibility / adaptability to different tasks and environments. A multi-modal legged robot can take the best of both worlds. In this paper, we propose a multi-modal locomotion framework that is composed of a hand-crafted transition motion and a learning-based bipedal controller-learnt by a novel algorithm called Automated Residual Reinforcement Learning. This framework aims to endow arbitrary quadruped robots with the ability to walk bipedally. In particular, we 1) design an additional supporting structure for a quadruped robot and a sequential multi-modal transition strategy; 2) propose a novel class of Reinforcement Learning algorithms for bipedal control and evaluate their performances in both simulation and the real world. Experimental results show that our proposed algorithms have the best performance in simulation and maintain a good performance in a real-world robot. Overall, our multi-modal robot could successfully switch between biped and quadruped, and walk in both modes. Experiment videos and code are available at https://chenaah.github.io/multimodal/.

show abstract

“…(vii) NGOpt [21] is an algorithm which automatically selects the right evolutionary algorithm to be trained out of a set of several algorithms, according to the properties of the optimization problem. NGOpt is implemented in the Nevergrad package.…”

Section: B Experiments For One Master Face Imagementioning

confidence: 99%

Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution

Shmelkin¹,

Friedlander²,

Wolf³

2021

Preprint

View full text Add to dashboard Cite

A master face is a face image that passes facebased identity-authentication for a large portion of the population. These faces can be used to impersonate, with a high probability of success, any user, without having access to any user-information. We optimize these faces, by using an evolutionary algorithm in the latent embedding space of the StyleGAN face generator. Multiple evolutionary strategies are compared, and we propose a novel approach that employs a neural network in order to direct the search in the direction of promising samples, without adding fitness evaluations. The results we present demonstrate that it is possible to obtain a high coverage of the LFW identities (over 40%) with less than 10 master faces, for three leading deep face recognition systems.

show abstract

Versatile black-box optimization

Cited by 20 publications

References 39 publications

IOHanalyzer: Detailed Performance Analyses for Iterative Optimization Heuristics

IOHanalyzer: Detailed Performance Analyses for Iterative Optimization Heuristics

Multi-Modal Legged Locomotion Framework with Automated Residual Reinforcement Learning

Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution

Contact Info

Product

Resources

About