English
Related papers

Related papers: Reparameterizable Subset Sampling via Continuous R…

200 papers

The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to large combinatorial distributions is still outstanding. Working…

Machine Learning · Statistics 2021-03-02 Max B. Paulus , Dami Choi , Daniel Tarlow , Andreas Krause , Chris J. Maddison

The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities. Over the past years, the machine learning community has proposed several extensions of this trick to…

Machine Learning · Computer Science 2022-03-09 Iris A. M. Huijben , Wouter Kool , Max B. Paulus , Ruud J. G. van Sloun

Estimating the gradients of stochastic nodes in stochastic computational graphs is one of the crucial research questions in the deep generative modeling community, which enables the gradient descent optimization on neural network…

Machine Learning · Computer Science 2023-02-23 Weonyoung Joo , Dongjun Kim , Seungjae Shin , Il-Chul Moon

The Gumbel-Softmax is a continuous distribution over the simplex that is often used as a relaxation of discrete distributions. Because it can be readily interpreted and easily reparameterized, it enjoys widespread use. We propose a modular…

Machine Learning · Statistics 2022-08-30 Andres Potapczynski , Gabriel Loaiza-Ganem , John P. Cunningham

ML models often operate within the context of a larger system that can adapt its response when the ML model is uncertain, such as falling back on safe defaults or a human in the loop. This commonly encountered operational context calls for…

Machine Learning · Computer Science 2022-11-22 Mahmoud Salem , Mohamed Osama Ahmed , Frederick Tung , Gabriel Oliveira

The well-known Gumbel-Max trick for sampling from a categorical distribution can be extended to sample $k$ elements without replacement. We show how to implicitly apply this 'Gumbel-Top-$k$' trick on a factorized distribution over…

Machine Learning · Computer Science 2019-05-31 Wouter Kool , Herke van Hoof , Max Welling

In computer science, there exist a large number of optimization problems defined on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some…

Machine Learning · Computer Science 2020-04-17 Yaoxin Li , Jing Liu , Guozheng Lin , Yueyuan Hou , Muyun Mou , Jiang Zhang

Variational inference using the reparameterization trick has enabled large-scale approximate Bayesian inference in complex probabilistic models, leveraging stochastic optimization to sidestep intractable expectations. The reparameterization…

Machine Learning · Statistics 2020-02-13 Christian A. Naesseth , Francisco J. R. Ruiz , Scott W. Linderman , David M. Blei

Large and performant neural networks are often overparameterized and can be drastically reduced in size and complexity thanks to pruning. Pruning is a group of methods, which seeks to remove redundant or unnecessary weights or groups of…

Computer Vision and Pattern Recognition · Computer Science 2023-02-15 Robin Dupont , Mohammed Amine Alaoui , Hichem Sahbi , Alice Lebois

Variational approximations are increasingly based on gradient-based optimization of expectations estimated by sampling. Handling discrete latent variables is then challenging because the sampling process is not differentiable. Continuous…

Machine Learning · Computer Science 2021-02-09 Tomasz Kuśmierczyk , Arto Klami

The rapid increase in the parameters of deep learning models has led to significant costs, challenging computational efficiency and model interpretability. In this paper, we introduce a novel and straightforward neural network pruning…

Machine Learning · Computer Science 2023-11-23 Zhang Zhang , Ruyi Tao , Jiang Zhang

Categorical variables are a natural choice for representing discrete structure in the world. However, stochastic neural networks rarely use categorical latent variables due to the inability to backpropagate through samples. In this work, we…

Machine Learning · Statistics 2017-08-08 Eric Jang , Shixiang Gu , Ben Poole

Compressed sensing (CS) MRI relies on adequate undersampling of the k-space to accelerate the acquisition without compromising image quality. Consequently, the design of optimal sampling patterns for these k-space coefficients has received…

Image and Video Processing · Electrical Eng. & Systems 2021-01-26 Iris A. M. Huijben , Bastiaan S. Veeling , Ruud J. G. van Sloun

Accurately reconstructing and forecasting ocean fields from sparse observations is critical for both operational and scientific purposes. Optimizing sensor placement to maximize reconstruction skill remains challenging due to evolving ocean…

Atmospheric and Oceanic Physics · Physics 2026-04-27 Oscar Chapron , Ronan Fablet , Yann Stéphan

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically…

Machine Learning · Computer Science 2020-12-29 Gonçalo M. Correia , Vlad Niculae , Wilker Aziz , André F. T. Martins

In many applications we seek to maximize an expectation with respect to a distribution over discrete variables. Estimating gradients of such objectives with respect to the distribution parameters is a challenging problem. We analyze…

Machine Learning · Statistics 2019-06-18 Evgeny Andriyash , Arash Vahdat , Bill Macready

The Gumbel trick is a method to sample from a discrete probability distribution, or to estimate its normalizing partition function. The method relies on repeatedly applying a random perturbation to the distribution in a particular way, each…

Machine Learning · Statistics 2017-06-14 Matej Balog , Nilesh Tripuraneni , Zoubin Ghahramani , Adrian Weller

Although deep neural networks have provided impressive gains in performance, these improvements often come at the cost of increased computational complexity and expense. In many cases, such as 3D volume or video classification tasks, not…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Sharath M Shankaranarayana , Soumava Kumar Roy , Prasad Sudhakar , Chandan Aladahalli

Structured latent variables allow incorporating meaningful prior knowledge into deep learning models. However, learning with such variables remains challenging because of their discrete nature. Nowadays, the standard learning approach is to…

Machine Learning · Computer Science 2021-10-29 Kirill Struminsky , Artyom Gadetsky , Denis Rakitin , Danil Karpushkin , Dmitry Vetrov

Sorting input objects is an important step in many machine learning pipelines. However, the sorting operator is non-differentiable with respect to its inputs, which prohibits end-to-end gradient-based optimization. In this work, we propose…

Machine Learning · Statistics 2019-04-30 Aditya Grover , Eric Wang , Aaron Zweig , Stefano Ermon
‹ Prev 1 2 3 10 Next ›