289 citations · 395 across the 10 of their papers we have counts for
12 papers
Generative Models of Multi-channel Data from a Single Example -- Application to Dust Emission
Bruno Régaldo-Saint Blancard, Erwan Allys, Constant Auclair +5
The quest for primordial -modes in the cosmic microwave background has emphasized the need for refined models of the Galactic dust foreground. Here, we aim at building a realist…
Generalized Rectifier Wavelet Covariance Models For Texture Synthesis
Antoine Brochard, Sixin Zhang, Stéphane Mallat
State-of-the-art maximum entropy models for texture synthesis are built from statistics relying on image representations defined by convolutional neural networks (CNN). Such repres…
On the Nash equilibrium of moment-matching GANs for stationary Gaussian processes
Sixin Zhang
Generative Adversarial Networks (GANs) learn an implicit generative model from data samples through a two-player game. In this paper, we study the existence of Nash equilibrium of…
Leveraging Joint-Diagonalization in Transform-Learning NMF
Sixin Zhang, Emmanuel Soubies, Cédric Févotte
Non-negative matrix factorization with transform learning (TL-NMF) is a recent idea that aims at learning data representations suited to NMF. In this work, we relate TL-NMF to the…
Particle gradient descent model for point process generation
Antoine Brochard, Bartłomiej Błaszczyszyn, Stéphane Mallat +1
This paper presents a statistical model for stationary ergodic point processes, estimated from a single realization observed in a square window. With existing approaches in stochas…
Data Assimilation Networks
Pierre Boudier, Anthony Fillion, Serge Gratton +2
Data assimilation (DA) aims at forecasting the state of a dynamical system by combining a mathematical representation of the system with noisy observations taking into account thei…
Maximum Entropy Models from Phase Harmonic Covariances
Sixin Zhang, Stéphane Mallat
The covariance of a stationary process is diagonalized by a Fourier transform. It does not take into account the complex Fourier phase and defines Gaussian maximum entropy mode…
Statistical learning of geometric characteristics of wireless networks
Antoine Brochard, Bartłomiej Błaszczyszyn, Stéphane Mallat +1
Motivated by the prediction of cell loads in cellular networks, we formulate the following new, fundamental problem of statistical learning of geometric marks of point processes: A…
Phase Harmonic Correlations and Convolutional Neural Networks
Stéphane Mallat, Sixin Zhang, Gaspar Rochette
A major issue in harmonic analysis is to capture the phase dependence of frequency representations, which carries important signal properties. It seems that convolutional neural ne…
Distributed stochastic optimization for deep learning (thesis)
Sixin Zhang
We study the problem of how to distribute the training of large-scale deep learning models in the parallel computing environment. We propose a new distributed stochastic optimizati…
Deep learning with Elastic Averaging SGD
Sixin Zhang, Anna Choromanska, Yann LeCun
We study the problem of stochastic optimization for deep learning in the parallel computing environment under communication constraints. A new algorithm is proposed in this setting…
No More Pesky Learning Rates
Tom Schaul, Sixin Zhang, Yann LeCun
The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multipl…