55 citations · 209 across the 32 of their papers we have counts for
12 papers · 1 filter
A Geometric Framework for Understanding Memorization in Generative Models
Brendan Leigh Ross, Hamidreza Kamkari, Tongzi Wu +5
As deep generative models have progressed, recent work has shown them to be capable of memorizing and reproducing training datapoints when deployed. These findings call into questi…
Verifying the Union of Manifolds Hypothesis for Image Data
Bradley C. A. Brown, Anthony L. Caterini, Brendan Leigh Ross +2
Deep learning has had tremendous success at learning low-dimensional representations of high-dimensional data. This success would be impossible if there was no hidden low-dimension…
Neural Implicit Manifold Learning for Topology-Aware Density Estimation
Brendan Leigh Ross, Gabriel Loaiza-Ganem, Anthony L. Caterini +1
Natural data observed in is often constrained to an -dimensional manifold , where . This work focuses on the task of building theoretically pr…
On the Normalizing Constant of the Continuous Categorical Distribution
Elliott Gordon-Rodriguez, Gabriel Loaiza-Ganem, Andres Potapczynski +1
Probability distributions supported on the simplex enjoy a wide range of applications across statistics and machine learning. Recently, a novel family of such distributions has bee…
Diagnosing and Fixing Manifold Overfitting in Deep Generative Models
Gabriel Loaiza-Ganem, Brendan Leigh Ross, Jesse C. Cresswell +1
Likelihood-based, or explicit, deep generative models use neural networks to construct flexible high-dimensional densities. This formulation directly contradicts the manifold hypot…
Entropic Issues in Likelihood-Based OOD Detection
Anthony L. Caterini, Gabriel Loaiza-Ganem
Deep generative models trained by maximum likelihood remain very popular methods for reasoning about data probabilistically. However, it has been observed that they can assign high…
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…
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…
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…
Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax
Andres Potapczynski, Gabriel Loaiza-Ganem, John P. Cunningham
The Gumbel-Softmax is a continuous distribution over the simplex that is often used as a relaxation of discrete distributions. Because it can be readily interpreted and easily repa…
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…
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…