paper-with-me

Papers

Neural Variational Inference and Learning in Undirected Graphical Models

2017-11-07 · NeurIPS 2017 12 · Volodymyr Kuleshov, Stefano Ermon

Many problems in machine learning are naturally expressed in the language of undirected graphical models. Here, we propose black-box learning and inference algorithms for undirected models that optimize a variational approximation to the log-likelihood of the model. Central to our approach is an upper bound on the log-partition function parametrized by a function q that we express as a flexible neural network. Our bound makes it possible to track the partition function during learning, to speed-up sampling, and to train a broad class of hybrid directed/undirected models via a unified variational inference framework. We empirically demonstrate the effectiveness of our method on several popular generative modeling datasets.

📄 PDF Abstract BibTeX arXiv:1711.02679

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Similar Papers 제목 키워드 기반

Variational Inference for Sparse and Undirected Models

2016-02-11 · ICML 2017 8 · John Ingraham, Debora Marks

Undirected graphical models are applied in genomics, protein structure prediction, and neuroscience to identify sparse interactions that underlie discrete data. Although Bayesian methods for inference would be favorable …

Bayesian InferenceProtein Structure PredictionVariational Inference

Pen and Paper Exercises in Machine Learning

2022-06-27 · Michael U. Gutmann

This is a collection of (mostly) pen-and-paper exercises in machine learning. The exercises are on the following topics: linear algebra, optimisation, directed graphical models, undirected graphical models, expressive po…

BIG-bench Machine Learning

Learning undirected models via query training

2019-12-05 · pproximateinference AABI Symposium 2019 12 · Miguel Lazaro-Gredilla, Wolfgang Lehrach, Dileep George

Typical amortized inference in variational autoencoders is specialized for a single probabilistic query. Here we propose an inference network architecture that generalizes to unseen probabilistic queries. Instead of an e…

Decoder

Undirected Graphical Models as Approximate Posteriors

2019-01-11 · ICML 2020 1 · Arash Vahdat, Evgeny Andriyash, William G. Macready

The representation of the approximate posterior is a critical aspect of effective variational autoencoders (VAEs). Poor choices for the approximate posterior have a detrimental impact on the generative performance of VAE…

Bayesian Inference

Variational Noise-Contrastive Estimation

2018-10-18 · Benjamin Rhodes, Michael Gutmann

Unnormalised latent variable models are a broad and flexible class of statistical models. However, learning their parameters from data is intractable, and few estimation techniques are currently available for such models…

parameter estimationVariational Inference