Oops I Took A Gradient: Scalable Sampling for Discrete Distributions

• URL: http://arxiv.org/abs/2102.04509v1
• Date: Mon, 8 Feb 2021 20:08:50 GMT
• Title: Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
• Authors: Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison
• Abstract summary: We show that this approach outperforms generic samplers in a number of difficult settings. We also demonstrate the use of our improved sampler for training deep energy-based models on high dimensional discrete data.
• Score: 53.3142984019796
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respect to its discrete inputs to propose updates in a Metropolis-Hastings sampler. We show empirically that this approach outperforms generic samplers in a number of difficult settings including Ising models, Potts models, restricted Boltzmann machines, and factorial hidden Markov models. We also demonstrate the use of our improved sampler for training deep energy-based models on high dimensional discrete data. This approach outperforms variational auto-encoders and existing energy-based models. Finally, we give bounds showing that our approach is near-optimal in the class of samplers which propose local updates.

Related papers

• Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers [49.1574468325115]
  We introduce a unified convergence analysis framework for deterministic samplers. Our framework achieves iteration complexity of $tilde O(d2/epsilon)$. We also provide a detailed analysis of Denoising Implicit Diffusion Models (DDIM)-type samplers.
  arXiv  Detail & Related papers  (2024-10-18T07:37:36Z)
• Self-Guided Generation of Minority Samples Using Diffusion Models [57.319845580050924]
  We present a novel approach for generating minority samples that live on low-density regions of a data manifold. Our framework is built upon diffusion models, leveraging the principle of guided sampling. Experiments on benchmark real datasets demonstrate that our approach can greatly improve the capability of creating realistic low-likelihood minority instances.
  arXiv  Detail & Related papers  (2024-07-16T10:03:29Z)
• A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization [7.378582040635655]
  Current deep learning approaches rely on generative models that yield exact sample likelihoods. This work introduces a method that lifts this restriction and opens the possibility to employ highly expressive latent variable models. We experimentally validate our approach in data-free Combinatorial Optimization and demonstrate that our method achieves a new state-of-the-art on a wide range of benchmark problems.
  arXiv  Detail & Related papers  (2024-06-03T17:55:02Z)
• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• Differentiating Metropolis-Hastings to Optimize Intractable Densities [51.16801956665228]
  We develop an algorithm for automatic differentiation of Metropolis-Hastings samplers. We apply gradient-based optimization to objectives expressed as expectations over intractable target densities.
  arXiv  Detail & Related papers  (2023-06-13T17:56:02Z)
• Example-Based Sampling with Diffusion Models [7.943023838493658]
  diffusion models for image generation could be appropriate for learning how to generate point sets from examples. We propose a generic way to produce 2-d point sets imitating existing samplers from observed point sets using a diffusion model. We demonstrate how the differentiability of our approach can be used to optimize point sets to enforce properties.
  arXiv  Detail & Related papers  (2023-02-10T08:35:17Z)
• Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes [23.682509357305406]
  Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. We propose a novel Sparse Gaussian Process Bayesian Autoencoder model in which we impose fully sparse Gaussian Process priors on the latent space of a Bayesian Autoencoder.
  arXiv  Detail & Related papers  (2023-02-09T09:57:51Z)
• Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
  We take a two-step approach by first modeling the probability distribution and then sampling from that model. We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
  arXiv  Detail & Related papers  (2021-10-20T12:25:22Z)
• On the Variational Posterior of Dirichlet Process Deep Latent Gaussian Mixture Models [0.0]
  We present an alternative treatment of the variational posterior of the Dirichlet Process Deep Latent Gaussian Mixture Model (DP-DLGMM) We show that our model is capable of generating realistic samples for each cluster obtained, and manifests competitive performance in a semi-supervised setting.
  arXiv  Detail & Related papers  (2020-06-16T08:46:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.