174 citations · 256 across the 8 of their papers we have counts for
7 papers
Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates
Nicholas J. Irons, Meyer Scetbon, Soumik Pal +1
Triangular flows, also known as Knöthe-Rosenblatt measure couplings, comprise an important building block of normalizing flow models for generative modeling and density estimation,…
Target Propagation via Regularized Inversion
Vincent Roulet, Zaid Harchaoui
Target Propagation (TP) algorithms compute targets instead of gradients along neural networks and propagate them backward in a way that is similar yet different than gradient back-…
Entropy Regularized Optimal Transport Independence Criterion
Lang Liu, Soumik Pal, Zaid Harchaoui
We introduce an independence criterion based on entropy regularized optimal transport. Our criterion can be used to test for independence between two samples. We establish non-asym…
Fast and Simple Optimization for Poisson Likelihood Models
Niao He, Zaid Harchaoui, Yichen Wang +1
Poisson likelihood models have been prevalently used in imaging, social networks, and time series analysis. We propose fast, simple, theoretically-grounded, and versatile, optimiza…
EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow
Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui +1
We propose a novel approach for optical flow estimation , targeted at large displacements with significant oc-clusions. It consists of two steps: i) dense matching by edge-preservi…
Convolutional Kernel Networks
Julien Mairal, Piotr Koniusz, Zaid Harchaoui +1
An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of…