research
∙
06/07/2023
Multi-modal Latent Diffusion
Multi-modal data-sets are ubiquitous in modern applications, and multi-m...
share
research
∙
05/30/2023
One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models
Generative Models (GMs) have attracted considerable attention due to the...
research
∙
03/01/2023
Continuous-Time Functional Diffusion Processes
We introduce functional diffusion processes (FDPs), which generalize tra...
research
∙
06/10/2022
How Much is Enough? A Study on Diffusion Times in Score-based Generative Models
Score-based diffusion models are a class of generative models whose dyna...
research
∙
06/30/2021
Revisiting the Effects of Stochasticity for Hamiltonian Samplers
We revisit the theoretical properties of Hamiltonian stochastic differen...
research
∙
06/09/2020
Isotropic SGD: a Practical Approach to Bayesian Posterior Sampling
In this work we define a unified mathematical framework to deepen our un...
research
∙
10/21/2019
Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD
Large scale machine learning is increasingly relying on distributed opti...
research
∙
03/06/2018