Arbitrary Conditional Distributions with Energy
Dec 6, 2021
Speakers
Ryan R. Strauss
Speaker · 0 followers
Junier B. Oliva
Speaker · 0 followers
About
Modeling distributions of covariates, or density estimation, is a core challenge in unsupervised learning. However, the majority of work only considers the joint distribution, which has limited relevance to practical situations. A more general and useful problem is arbitrary conditional density estimation, which aims to model any possible conditional distribution over a set of covariates, reflecting the more realistic setting of inference based on prior knowledge. We propose a novel method, Arbitrary Conditioning with Energy (ACE), that can simultaneously estimate the distribution p(𝐱_u |𝐱_o) for all possible subsets of unobserved features 𝐱_u and observed features 𝐱_o. ACE is designed to avoid unnecessary bias and complexity — we specify densities with a highly expressive energy function and reduce the problem to only learning one-dimensional conditionals (from which more complex distributions can be recovered during inference). This results in an approach that is both simpler and higher-performing than prior methods. We show that ACE achieves state-of-the-art for arbitrary conditional likelihood estimation and data imputation on standard benchmarks.Modeling distributions of covariates, or density estimation, is a core challenge in unsupervised learning. However, the majority of work only considers the joint distribution, which has limited relevance to practical situations. A more general and useful problem is arbitrary conditional density estimation, which aims to model any possible conditional distribution over a set of covariates, reflecting the more realistic setting of inference based on prior knowledge. We propose a novel method, Arbi…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
H+AI:: Exploring the Dark Side of Human-AI Interaction
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Littlestone Classes are Privately Online Learnable
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Kernelized Heterogeneous Risk Minimization
Watch later
Jiashuo Liu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Data vast and low in variance: Augment machine learning pipelines with dataset profiles to improve data quality without sacrificing scale
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Reinforcement Learning Enhanced Explainer for Graph Neural Networks
Watch later
Caihua Shan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Nonparametric Volterra Kernels with Gaussian Processes
Watch later
Magnus Ross, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%