activity
20172022
most citedFew-Shot Diffusion Models

20 citations · 28 across the 3 of their papers we have counts for

collaborators

9 papers

cs.CV202220 cited

Few-Shot Diffusion Models

Giorgio Giannone, Didrik Nielsen, Ole Winther

Denoising diffusion probabilistic models (DDPM) are powerful hierarchical latent variable models with remarkable sample generation quality and training stability. These properties…

cs.LG20211 cited

Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC

Priyank Jaini, Didrik Nielsen, Max Welling

Hybrid Monte Carlo is a powerful Markov Chain Monte Carlo method for sampling from complex continuous distributions. However, a major limitation of HMC is its inability to be appli…

stat.ML2021

Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions

Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini +2

Generative flows and diffusion models have been predominantly trained on ordinal data, for example natural images. This paper introduces two extensions of flows and diffusion for c…

cs.LG2020

SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows

Didrik Nielsen, Priyank Jaini, Emiel Hoogeboom +2

Normalizing flows and variational autoencoders are powerful generative models that can represent complicated density functions. However, they both impose constraints on the models:…

cs.LG2020

Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow

Didrik Nielsen, Ole Winther

Flow models have recently made great progress at modeling ordinal discrete data such as images and audio. Due to the continuous nature of flow models, dequantization is typically a…

cs.LG2018

SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient

Aaron Mishkin, Frederik Kunstner, Didrik Nielsen +2

Uncertainty estimation in large deep-learning models is a computationally challenging task, where it is difficult to form even a Gaussian approximation to the posterior distributio…