activity
20122022
most citedUses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning

55 citations · 118 across the 12 of their papers we have counts for

collaborators
Showing stat.MLShow all

13 papers · 1 filter

stat.ML20212 cited

Rectangular Flows for Manifold Learning

Anthony L. Caterini, Gabriel Loaiza-Ganem, Geoff Pleiss +1

Normalizing flows are invertible neural networks with tractable change-of-volume terms, which allow optimization of their parameters to be efficiently performed via maximum likelih…

stat.ML202055 cited

Uses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning

Elliott Gordon-Rodriguez, Gabriel Loaiza-Ganem, Geoff Pleiss +1

Modern deep learning is primarily an experimental science, in which empirical advances occasionally come at the expense of probabilistic rigor. Here we focus on one such example; n…

stat.ML2020

The continuous categorical: a novel simplex-valued exponential family

Elliott Gordon-Rodriguez, Gabriel Loaiza-Ganem, John P. Cunningham

Simplex-valued data appear throughout statistics and machine learning, for example in the context of transfer learning and compression of deep networks. Existing models for this cl…

stat.ML2019

The continuous Bernoulli: fixing a pervasive error in variational autoencoders

Gabriel Loaiza-Ganem, John P. Cunningham

Variational autoencoders (VAE) have quickly become a central tool in machine learning, applicable to a broad range of data types and latent variable models. By far the most common…

stat.ML20195 cited

Approximating exponential family models (not single distributions) with a two-network architecture

Sean R. Bittner, John P. Cunningham

Recently much attention has been paid to deep generative models, since they have been used to great success for variational inference, generation of complex data types, and more. I…

stat.ML2019

Deep Random Splines for Point Process Intensity Estimation of Neural Population Data

Gabriel Loaiza-Ganem, Sean M. Perkins, Karen E. Schroeder +2

Gaussian processes are the leading class of distributions on random functions, but they suffer from well known issues including difficulty scaling and inflexibility with respect to…