Stochastic Gradient Descent as Approximate Bayesian Inference
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.
Code (1)
Tasks
Bayesian InferenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Stein Variational Gradient Descent for Approximate Bayesian Computation
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 InferenceBayesian Neural Network via Stochastic Gradient Descent
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 InferenceStochastic natural gradient descent draws posterior samples in function space
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…
validNeural Variational Gradient Descent
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 InferenceLarge-Scale Distributed Bayesian Matrix Factorization using Stochastic Gradient MCMC
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