output
20112020
most citedInformation-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles

205 citations

14 papers

stat.ML2020

Distribution-Based Invariant Deep Networks for Learning Meta-Features

Gwendoline De Bie, Herilalaina Rakotoarison, Gabriel Peyré +1

Recent advances in deep learning from probability distributions successfully achieve classification or regression from distribution samples, thus invariant under permutation of the…

cs.LG2020★ 1 cited

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…

eess.SP2019★ 10 cited

LEAP nets for power grid perturbations

Benjamin Donnot, Balthazar Donon, Isabelle Guyon +4

We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to t…

cs.LG2019★ 17 cited

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…

cond-mat.dis-nn2019★ 2 cited

Inverse problems for structured datasets using parallel TAP equations and RBM

Aurélien Decelle, Sungmin Hwang, Jacopo Rocchi +1

We propose an efficient algorithm to solve inverse problems in the presence of binary clustered datasets. We consider the paradigmatic Hopfield model in a teacher student scenario,…

cond-mat.dis-nn2019★ 21 cited

Learning a Local Symmetry with Neural-Networks

Aurélien Decelle, Victor Martin-Mayor, Beatriz Seoane

We explore the capacity of neural networks to detect a symmetry with complex local and non-local patterns : the gauge symmetry Z 2 . This symmetry is present in physical problems f…

cs.LG2018★ 17 cited

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…

stat.ML2018★ 27 cited

Structural Agnostic Modeling: Adversarial Learning of Causal Graphs

Diviyan Kalainathan, Olivier Goudet, Isabelle Guyon +2

A new causal discovery method, Structural Agnostic Modeling (SAM), is presented in this paper. Leveraging both conditional independencies and distributional asymmetries, SAM aims t…

cs.NE2018★ 36 cited

The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities

Joel Lehman, Jeff Clune, Dusan Misevic +50

Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them. However, because evolution is an algorithmic pr…

cond-mat.dis-nn2018★ 55 cited

Thermodynamics of Restricted Boltzmann Machines and related learning dynamics

Aurélien Decelle, Giancarlo Fissore, Cyril Furtlehner

We investigate the thermodynamic properties of a Restricted Boltzmann Machine (RBM), a simple energy-based generative model used in the context of unsupervised learning. Assuming t…

cs.CV2018★ 8 cited

Coarse to fine non-rigid registration: a chain of scale-specific neural networks for multimodal image alignment with application to remote sensing

Armand Zampieri, Guillaume Charpiat, Yuliya Tarabalka

We tackle here the problem of multimodal image non-rigid registration, which is of prime importance in remote sensing and medical imaging. The difficulties encountered by classical…

cs.CV2018★ 34 cited

Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos

Hugo Jair Escalante, Heysem Kaya, Albert Ali Salah +14

Explainability and interpretability are two critical aspects of decision support systems. Within computer vision, they are critical in certain tasks related to human behavior analy…

cs.DL2017★ 48 cited

Design and Analysis of the NIPS 2016 Review Process

Nihar B. Shah, Behzad Tabibian, Krikamol Muandet +2

Neural Information Processing Systems (NIPS) is a top-tier annual conference in machine learning. The 2016 edition of the conference comprised more than 2,400 paper submissions, 3,…

math.OC2011★ 205 cited

Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles

Yann Ollivier, Ludovic Arnold, Anne Auger +1

We present a canonical way to turn any smooth parametric family of probability distributions on an arbitrary search space into a continuous-time black-box optimization method o…