205 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Laboratoire de Recherche en InformatiqueFR9 papers
- Université Paris-SudFR6 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- Institut national de recherche en sciences et technologies du numériqueFR4 papers
- Université Paris-SaclayFR4 papers
- Meta (United States)US3 papers
- Centre Inria de SaclayFR2 papers
- ChaLearn2 papers
- National Institute of Astrophysics, Optics and ElectronicsMX2 papers
- Sorbonne UniversitéFR2 papers
- Tel Aviv UniversityIL2 papers
- 4Thparadigm (China)1 paper
3 papers · 1 filter
An Equivalence between Bayesian Priors and Penalties in Variational Inference
Pierre Wolinski, Guillaume Charpiat, Yann Ollivier
In machine learning, it is common to optimize the parameters of a probabilistic model, modulated by an ad hoc regularization term that penalizes some values of the parameters. Regu…
Towards AutoML in the presence of Drift: first results
Jorge G. Madrid, Hugo Jair Escalante, Eduardo F. Morales +5
Research progress in AutoML has lead to state of the art solutions that can cope quite wellwith supervised learning task, e.g., classification with AutoSklearn. However, so far the…
Can recurrent neural networks warp time?
Corentin Tallec, Yann Ollivier
Successful recurrent models such as long short-term memories (LSTMs) and gated recurrent units (GRUs) use ad hoc gating mechanisms. Empirically these models have been found to impr…