Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions

DOI10.1007/s11590-022-01895-5OpenAlexW4287200304MaRDI QIDQ2693789

Michael C. Burkhart

Publication date: 24 March 2023

Published in: Optimization Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2104.12949

zbMATH Keywords

sequential Bayesian inferencediscriminative Bayesian filteringmomentum in optimizationstochastic Newton method

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Convex programming (90C25) Newton-type methods (49M15) Stochastic programming (90C15)

Uses Software

• tn
• STRUCTURE
• AdaGrad

Cites Work

• Stochastic global optimization as a filtering problem
• Incremental proximal methods for large scale convex optimization
• On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix
• A simplified neuron model as a principal component analyzer
• A survey of truncated-Newton methods
• Sub-sampled Newton methods
• Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods
• Minimization of functions having Lipschitz continuous first partial derivatives
• Adaptive stochastic approximation by the simultaneous perturbation method
• Hybrid Deterministic-Stochastic Methods for Data Fitting
• Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence
• On the Use of Stochastic Hessian Information in Optimization Methods for Machine Learning
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Acceleration of Stochastic Approximation by Averaging
• Gaussian filters for nonlinear filtering problems
• Adaptive Sampling Strategies for Stochastic Optimization
• A Mean-Field Optimal Control Formulation for Global Optimization
• Probabilistic Line Searches for Stochastic Optimization
• Optimization Methods for Large-Scale Machine Learning
• 10.1162/jmlr.2003.3.4-5.993
• Incremental Least Squares Methods and the Extended Kalman Filter
• The Discriminative Kalman Filter for Bayesian Filtering with Nonlinear and Nongaussian Observation Models
• An investigation of Newton-Sketch and subsampled Newton methods
• Robust Closed-Loop Control of a Cursor in a Person with Tetraplegia using Gaussian Process Regression
• A Stochastic Line Search Method with Expected Complexity Analysis
• Elements of Information Theory
• Some methods of speeding up the convergence of iteration methods
• Monte Carlo techniques to estimate the conditional expectation in multi-stage non-linear filtering†
• A Stochastic Approximation Method
• Exact and inexact subsampled Newton methods for optimization
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions