paper-with-me

Papers

Analytically Tractable Inference in Deep Neural Networks

2021-03-09 · Luong-Ha Nguyen, James-A. Goulet

Since its inception, deep learning has been overwhelmingly reliant on backpropagation and gradient-based optimization algorithms in order to learn weight and bias parameter values. Tractable Approximate Gaussian Inference (TAGI) algorithm was shown to be a viable and scalable alternative to backpropagation for shallow fully-connected neural networks. In this paper, we are demonstrating how TAGI matches or exceeds the performance of backpropagation, for training classic deep neural network architectures. Although TAGI's computational efficiency is still below that of deterministic approaches relying on backpropagation, it outperforms them on classification tasks and matches their performance for information maximizing generative adversarial networks while using smaller architectures trained with fewer epochs.

📄 PDF Abstract BibTeX arXiv:2103.05461

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

Analytically Tractable Hidden-States Inference in Bayesian Neural Networks

2021-07-08 · Luong-Ha Nguyen, James-A. Goulet

With few exceptions, neural networks have been relying on backpropagation and gradient descent as the inference engine in order to learn the model parameters, because the closed-form Bayesian inference for neural network…

Adversarial AttackBayesian Inference

Variational Learning for the Inverted Beta-Liouville Mixture Model and Its Application to Text Categorization

2021-12-29 · Yongfa Ling, Wenbo Guan, Qiang Ruan, Heping Song 외

The finite invert Beta-Liouville mixture model (IBLMM) has recently gained some attention due to its positive data modeling capability. Under the conventional variational inference (VI) framework, the analytically tracta…

ObjectText CategorizationVariational Inference

Mean-Field Variational Inference for Gradient Matching with Gaussian Processes

2016-10-21 · Nico S. Gorbach, Stefan Bauer, Joachim M. Buhmann

Gradient matching with Gaussian processes is a promising tool for learning parameters of ordinary differential equations (ODE's). The essence of gradient matching is to model the prior over state variables as a Gaussian …

Gaussian ProcessesVariational Inference

Variational inference for Markov jump processes

2007-12-01 · NeurIPS 2007 12 · Manfred Opper, Guido Sanguinetti

Markov jump processes play an important role in a large number of application domains. However, realistic systems are analytically intractable and they have traditionally been analysed using simulation based techniques, …

parameter estimationVariational Inference

A probabilistic model for the numerical solution of initial value problems

2016-10-17 · Michael Schober, Simo Särkkä, Philipp Hennig

Like many numerical methods, solvers for initial value problems (IVPs) on ordinary differential equations estimate an analytically intractable quantity, using the results of tractable computations as inputs. This structu…