1.4k citations
- Université Paris-SudFR237 papers
- Centre National de la Recherche ScientifiqueFR177 papers
- Institut national de recherche en sciences et technologies du numériqueFR105 papers
- Université Paris-SaclayFR70 papers
- Centre Inria de SaclayFR53 papers
- University of California, BerkeleyUS34 papers
- Institut d'Astrophysique SpatialeFR30 papers
- Université Paris DiderotFR30 papers
- Sapienza University of RomeIT27 papers
- Université Toulouse III - Paul SabatierFR27 papers
- University of California, DavisUS27 papers
- California Institute of TechnologyUS26 papers
15 papers · 1 filter
On the Behaviour of Differential Evolution for Problems with Dynamic Linear Constraints
Maryam Hasani-Shoreh, María-Yaneli Ameca-Alducin, Wilson Blaikie +2
Evolutionary algorithms have been widely applied for solving dynamic constrained optimization problems (DCOPs) as a common area of research in evolutionary optimization. Current be…
Unbiasing Truncated Backpropagation Through Time
Corentin Tallec, Yann Ollivier
Truncated Backpropagation Through Time (truncated BPTT) is a widespread method for learning recurrent computational graphs. Truncated BPTT keeps the computational benefits of Backp…
Unbiased Online Recurrent Optimization
Corentin Tallec, Yann Ollivier
The novel Unbiased Online Recurrent Optimization (UORO) algorithm allows for online learning of general recurrent computational graphs such as recurrent network models. It works in…
COCO: Performance Assessment
Nikolaus Hansen, Anne Auger, Dimo Brockhoff +2
We present an any-time performance assessment for benchmarking numerical optimization algorithms in a black-box scenario, applied within the COCO benchmarking platform. The perform…
Biobjective Performance Assessment with the COCO Platform
Dimo Brockhoff, Tea Tušar, Dejan Tušar +3
This document details the rationales behind assessing the performance of numerical black-box optimizers on multi-objective problems within the COCO platform and in particular on th…
Practical Riemannian Neural Networks
Gaétan Marceau-Caron, Yann Ollivier
We provide the first experimental results on non-synthetic datasets for the quasi-diagonal Riemannian gradient descents for neural networks introduced in [Ollivier, 2015]. These in…