scientific article; zbMATH DE number 7307488

MaRDI QIDQ5149258zbMATH OpenFDO

Authors Frederik Heber, Zofia Trstanova, Benedict Leimkuhler

Publication date 8 February 2021

Full work available at URL https://jmlr.csail.mit.edu/papers/v21/19-339.html

zbMATH Keywords

Markov chain Monte Carloneural network trainingBayesian posterior samplingensemble sampling strategiessoftware platforms for machine learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning to optimize via posterior sampling
• Parametric Inference for Discretely Sampled Stochastic Differential Equations
• Variational Inference for Stochastic Differential Equations
• Posterior inference on parameters of stochastic differential equations via non-linear Gaussian filtering and adaptive MCMC
• Randomized maximum likelihood based posterior sampling
• Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations
• Laplace based approximate posterior inference for differential equation models
• Discrete sample estimation for gaussian random fields generated by stochastic partial differential equations
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations

Cites work

• Adaptive subgradient methods for online learning and stochastic optimization
• Are Loss Functions All the Same?
• Computational complexity of Metropolis-Hastings methods in high dimensions
• Ensemble preconditioning for Markov chain Monte Carlo simulation
• Ensemble samplers with affine invariance
• Entropy-SGD: biasing gradient descent into wide valleys
• Exploration of the (non-)asymptotic bias and variance of stochastic gradient Langevin dynamics
• Flat Minima
• Free energy computations. A mathematical perspective
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• How to generate random matrices from the classical compact groups
• Local and global perspectives on diffusion maps in the analysis of molecular systems
• Long-run accuracy of variational integrators in the stochastic context
• Machine learning in computer vision.
• Molecular dynamics. With deterministic and stochastic numerical methods
• Numerical Optimization
• Optimization methods for large-scale machine learning
• Rational construction of stochastic numerical methods for molecular sampling
• Statistics in the big data era: failures of the machine
• The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics
• The concentration of measure phenomenon
• The simulated tempering method in the infinite switch limit with adaptive weight learning
• Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks

Cited in

(3)

• Gibbs sampling the posterior of neural networks
• Efficient Bayes inference in neural networks through adaptive importance sampling
• Affine-invariant ensemble transform methods for logistic regression

Describes a project that uses

Uses Software

• AlexNet
• EnsembleQN
• RMSprop
• ImageNet

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5149258)