Didrik Nielsen
6 papers · 2018–2021 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot (3) π Cross-Pollinator (13) π Renaissance Researcher (5) π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(12)
π§
Keyword Pioneer
Conferences
NIPS (4)
AISTATS (1)
ICML (1)
Top co-authors
Keywords
variational inference
(4)
normalizing flow
(4)
natural gradient
(2)
generative model
(2)
mean-field approximation
(1)
likelihood estimation
(1)
discrete sampling
(1)
diffusion model
(1)
autoregressive model
(1)
variational autoencoder
(1)
uncertainty estimation
(1)
bayesian deep learning
(1)
combinatorial space
(1)
gaussian model
(1)
categorical distribution
(1)
covariance approximation
(1)
survae flow
(1)
image segmentation
(1)
surjective transformation
(1)
uncertainty quantification
(1)
Papers
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
NIPS 2021
Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC
AISTATS 2021
Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
NIPS 2020
SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
NIPS 2020
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient
NIPS 2018
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
ICML 2018