paper-with-me

홈 › Papers

Stability Regularization for Discrete Representation Learning

2021-09-29 · ICLR 2022 4 · Adeel Pervez, Efstratios Gavves

We present a method for training neural network models with discrete stochastic variables. The core of the method is \emph{stability regularization}, which is a regularization procedure based on the idea of noise stability developed in Gaussian isoperimetric theory in the analysis of Gaussian functions. Stability regularization is method to make the output of continuous functions of Gaussian random variables close to discrete, that is binary or categorical, without the need for significant manual tuning. The method allows control over the extent to which a Gaussian function's output is close to discrete, thus allowing for continued flow of gradient. The method can be used standalone or in combination with existing continuous relaxation methods. We validate the method in a broad range of experiments using discrete variables including neural relational inference, generative modeling, clustering and conditional computing.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Temporal Regularization in Markov Decision Process

2018-11-01 · Pierre Thodoroff, Audrey Durand, Joelle Pineau, Doina Precup

Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to re…

Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Temporal Regularization for Markov Decision Process

2018-12-01 · NeurIPS 2018 12 · Pierre Thodoroff, Audrey Durand, Joelle Pineau, Doina Precup

Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to re…

Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport

2021-10-25 · Alex Delalande

We derive nearly tight and non-asymptotic convergence bounds for solutions of entropic semi-discrete optimal transport. These bounds quantify the stability of the dual solutions of the regularized problem (sometimes call…

3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model

2018-03-20 · Jin Zeng, Gene Cheung, Michael Ng, Jiahao Pang 외

3D point cloud - a new signal representation of volumetric objects - is a discrete collection of triples marking exterior object surface locations in 3D space. Conventional imperfect acquisition processes of 3D point clo…

Denoisinggraph constructionStereo MatchingStereo Matching Hand

How more data can hurt: Instability and regularization in next-generation reservoir computing

2024-07-11 · Yuanzhao Zhang, Edmilson Roque dos Santos, Sean P. Cornelius

It has been found recently that more data can, counter-intuitively, hurt the performance of deep neural networks. Here, we show that a more extreme version of the phenomenon occurs in data-driven models of dynamical syst…