paper-with-me

Papers

Stochastic Gradient Descent as Approximate Bayesian Inference

2017-04-13 · Stephan Mandt, Matthew D. Hoffman, David M. Blei

Stochastic Gradient Descent with a constant learning rate (constant SGD) simulates a Markov chain with a stationary distribution. With this perspective, we derive several new results. (1) We show that constant SGD can be used as an approximate Bayesian posterior inference algorithm. Specifically, we show how to adjust the tuning parameters of constant SGD to best match the stationary distribution to a posterior, minimizing the Kullback-Leibler divergence between these two distributions. (2) We demonstrate that constant SGD gives rise to a new variational EM algorithm that optimizes hyperparameters in complex probabilistic models. (3) We also propose SGD with momentum for sampling and show how to adjust the damping coefficient accordingly. (4) We analyze MCMC algorithms. For Langevin Dynamics and Stochastic Gradient Fisher Scoring, we quantify the approximation errors due to finite learning rates. Finally (5), we use the stochastic process perspective to give a short proof of why Polyak averaging is optimal. Based on this idea, we propose a scalable approximate MCMC algorithm, the Averaged Stochastic Gradient Sampler.

📄 PDF Abstract BibTeX arXiv:1704.04289

Code (1)

taohu88/BayesianML

Tasks

Bayesian Inference

Methods 이 논문이 사용한 방법론

SGD with Momentum 설명 없음
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Stein Variational Gradient Descent for Approximate Bayesian Computation

2019-10-16 · pproximateinference AABI Symposium 2019 12 · Chunlin Ji, Jiangsheng Yi, Wanchuang Zhu

Approximate Bayesian Computation (ABC) provides a generic framework of Bayesian inference for likelihood-free models, but sampling based posterior approximation is often time-consuming and has difficulty accessing the co…

Bayesian InferenceVariational Inference

Bayesian Neural Network via Stochastic Gradient Descent

2020-06-04 · Abhinav Sagar

The goal of bayesian approach used in variational inference is to minimize the KL divergence between variational distribution and unknown posterior distribution. This is done by maximizing the Evidence Lower Bound (ELBO)…

regressionVariational Inference

Stochastic natural gradient descent draws posterior samples in function space

2018-06-25 · Samuel L. Smith, Daniel Duckworth, Semon Rezchikov, Quoc V. Le 외

Recent work has argued that stochastic gradient descent can approximate the Bayesian uncertainty in model parameters near local minima. In this work we develop a similar correspondence for minibatch natural gradient desc…

valid

Neural Variational Gradient Descent

2021-07-22 · pproximateinference AABI Symposium 2022 2 · Lauro Langosco di Langosco, Vincent Fortuin, Heiko Strathmann

Particle-based approximate Bayesian inference approaches such as Stein Variational Gradient Descent (SVGD) combine the flexibility and convergence guarantees of sampling methods with the computational benefits of variati…

Bayesian InferenceregressionVariational Inference

Large-Scale Distributed Bayesian Matrix Factorization using Stochastic Gradient MCMC

2015-03-05 · Sungjin Ahn, Anoop Korattikara, Nathan Liu, Suju Rajan 외

Despite having various attractive qualities such as high prediction accuracy and the ability to quantify uncertainty and avoid over-fitting, Bayesian Matrix Factorization has not been widely adopted because of the prohib…

Prediction