paper-with-me

Papers

Efficient Language Modeling with Automatic Relevance Determination in Recurrent Neural Networks

2019-08-01 · WS 2019 8 · Maxim Kodryan, Artem Grachev, Dmitry Ignatov, Dmitry Vetrov

Reduction of the number of parameters is one of the most important goals in Deep Learning. In this article we propose an adaptation of Doubly Stochastic Variational Inference for Automatic Relevance Determination (DSVI-ARD) for neural networks compression. We find this method to be especially useful in language modeling tasks, where large number of parameters in the input and output layers is often excessive. We also show that DSVI-ARD can be applied together with encoder-decoder weight tying allowing to achieve even better sparsity and performance. Our experiments demonstrate that more than 90{\%} of the weights in both encoder and decoder layers can be removed with a minimal quality loss.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderLanguage ModelingLanguage ModellingVariational Inference

Methods 이 논문이 사용한 방법론

Weight Tying Weight Tying improves the performance of language models by tying (sharing) the weights of the embedding and softmax layers. This…

Similar Papers 제목 키워드 기반

Laplacian Prior Variational Automatic Relevance Determination for Transmission Tomography

2017-10-26 · Jingwei Lu, David G. Politte, Joseph A. O'Sullivan

In the classic sparsity-driven problems, the fundamental L-1 penalty method has been shown to have good performance in reconstructing signals for a wide range of problems. However this performance relies on a good choice…

An Automatic Relevance Determination Prior Bayesian Neural Network for Controlled Variable Selection

2020-01-06 · Rendani Mbuvha, Illyes Boulkaibet, Tshilidzi Marwala

We present an Automatic Relevance Determination prior Bayesian Neural Network(BNN-ARD) weight l2-norm measure as a feature importance statistic for the model-x knockoff filter. We show on both simulated data and the Norw…

Feature ImportanceVariable Selection

Variable selection for Gaussian processes via sensitivity analysis of the posterior predictive distribution

2017-12-21 · Topi Paananen, Juho Piironen, Michael Riis Andersen, Aki Vehtari

Variable selection for Gaussian process models is often done using automatic relevance determination, which uses the inverse length-scale parameter of each input variable as a proxy for variable relevance. This implicitl…

Gaussian ProcessesSensitivityVariable Selection

Automatic Relevance Determination For Deep Generative Models

2015-05-28 · Theofanis Karaletsos, Gunnar Rätsch

A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space. In the context of belief networks with lat…

Model SelectionVariational Inference

Correntropy-Based Logistic Regression with Automatic Relevance Determination for Robust Sparse Brain Activity Decoding

2022-07-20 · Yuanhao Li, Badong Chen, Yuxi Shi, Natsue Yoshimura 외

Recent studies have utilized sparse classifications to predict categorical variables from high-dimensional brain activity signals to expose human's intentions and mental states, selecting the relevant features automatica…

Brain DecodingClassificationEEGElectroencephalogram (EEG)+1