scientific article; zbMATH DE number 6860839

zbMath1442.62055arXiv1704.04289MaRDI QIDQ4637063

David M. Blei, Matthew D. Hoffman, Stephan Mandt

Publication date: 17 April 2018

Full work available at URL: https://arxiv.org/abs/1704.04289

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

stochastic optimizationstochastic differential equationsvariational inferenceapproximate Bayesian inferencestochastic gradient MCMC

Mathematics Subject Classification ID

Bayesian inference (62F15) Monte Carlo methods (65C05) Stochastic approximation (62L20)

Related Items

Some Limit Properties of Markov Chains Induced by Recursive Stochastic Algorithms, On large batch training and sharp minima: a Fokker-Planck perspective, An online conjugate gradient algorithm for large-scale data analysis in machine learning, Gradient flows and randomised thresholding: sparse inversion and classification*, A heteroencoder architecture for prediction of failure locations in porous metals using variational inference, Challenges in Markov chain Monte Carlo for Bayesian neural networks, Laplacian smoothing gradient descent, A probabilistic approximate logic for neuro-symbolic learning and reasoning, Classification and image processing with a semi‐discrete scheme for fidelity forced Allen–Cahn on graphs, Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons, Bayesian Inverse Problems Are Usually Well-Posed, Data augmentation for Bayesian deep learning, Unnamed Item, Bridging the gap between constant step size stochastic gradient descent and Markov chains, Scalable Bayesian approach for the DINA Q-matrix estimation combining stochastic optimization and variational inference, Improving sampling accuracy of stochastic gradient MCMC methods via non-uniform subsampling of gradients, A Generalization Gap Estimation for Overparameterized Models via the Langevin Functional Variance, High‐dimensional limit theorems for SGD: Effective dynamics and critical scaling, Open Problem—Iterative Schemes for Stochastic Optimization: Convergence Statements and Limit Theorems, Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions, A Continuous-Time Analysis of Distributed Stochastic Gradient, Unnamed Item, Unnamed Item, Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach, On the convergence of stochastic approximations under a subgeometric ergodic Markov dynamic, Analysis of stochastic gradient descent in continuous time, Temporal mixture ensemble models for probabilistic forecasting of intraday cryptocurrency volume, Noise-induced degeneration in online learning, On stochastic mirror descent with interacting particles: convergence properties and variance reduction, Neural ODEs as the deep limit of ResNets with constant weights, Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression, Unnamed Item, Unnamed Item

Uses Software

• AdaGrad
• RMSprop
• ADVI
• Saga
• NUTS
• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A fast scoring algorithm for maximum likelihood estimation in unbalanced mixed models with nested random effects
• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• The free action of nonequilibrium dynamics
• Fixed-form variational posterior approximation through stochastic linear regression
• Stochastic methods. A handbook for the natural and social sciences
• Asymptotic methods in statistical decision theory
• An introduction to variational methods for graphical models
• Bridging the gap between constant step size stochastic gradient descent and Markov chains
• Efficient recursive estimation. Application to estimating the parameters of a covariance function
• Robust Stochastic Approximation Approach to Stochastic Programming
• Acceleration of Stochastic Approximation by Averaging
• An Introduction to Variational Autoencoders
• Some methods of speeding up the convergence of iteration methods
• A Stochastic Approximation Method
• Brownian motion in a field of force and the diffusion model of chemical reactions
• Variational Bayesian learning of directed graphical models with hidden variables