Valentin Dalibard
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Valentin Dalibard has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Chris Lu
University of Oxford, Oxford, United Kingdom
2 shared publications - Robert Lange
Technical Univ. Berlin, Berlin, Germany
2 shared publications - Sebastian Flennerhag
Google DeepMind, London, United Kingdom
2 shared publications - Tom Schaul
Google DeepMind, London, United Kingdom
2 shared publications - Tom Zahavy
Google DeepMind, London, United Kingdom
2 shared publications - Yutian Chen
Google DeepMind, London, United Kingdom
2 shared publications
Latest Publications
- Open Access
- 15 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 29-30
Discovering Evolution Strategies via Meta-Black-Box Optimization
- 15 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 29-30
Open AccessDiscovering Evolution Strategies via Meta-Black-Box Optimization
- Open Access
- 12 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 929-937
Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization
Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution. While they provide a general-purpose tool for optimization, their particular instantiations can be heuristic and motivated by loose biological intuition. In this work we explore a fundamentally different approach: Given a sufficiently flexible parametrization of the genetic operators, we discover entirely new genetic algorithms in a data-driven fashion. More specifically, we parametrize selection and mutation rate adaptation as cross- and self-attention modules and use Meta-Black-Box-Optimization to evolve their parameters on a set of diverse optimization tasks. The resulting Learned Genetic Algorithm outperforms state-of-the-art adaptive baseline genetic algorithms and generalizes far beyond its meta-training settings. The learned algorithm can be applied to previously unseen optimization problems, search dimensions & evaluation budgets. We conduct extensive analysis of the discovered operators and provide ablation experiments, which highlight the benefits of flexible module parametrization and the ability to transfer ('plug-in') the learned operators to conventional genetic algorithms.
- 12 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 929-937
Open AccessDiscovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization
Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution. While they provide a general-purpose tool for optimization, their particular instantiations can be heuristic and motivated by loose biological intuition. In this work we explore a fundamentally different approach: Given a sufficiently flexible parametrization of the genetic operators, we discover entirely new genetic algorithms in a data-driven fashion. More specifically, we parametrize selection and mutation rate adaptation as cross- and self-attention modules and use Meta-Black-Box-Optimization to evolve their parameters on a set of diverse optimization tasks. The resulting Learned Genetic Algorithm outperforms state-of-the-art adaptive baseline genetic algorithms and generalizes far beyond its meta-training settings. The learned algorithm can be applied to previously unseen optimization problems, search dimensions & evaluation budgets. We conduct extensive analysis of the discovered operators and provide ablation experiments, which highlight the benefits of flexible module parametrization and the ability to transfer ('plug-in') the learned operators to conventional genetic algorithms.