Analysis of stochastic gradient descent in continuous time
From MaRDI portal
Publication:2058762
DOI10.1007/s11222-021-10016-8zbMath1475.90105arXiv2004.07177OpenAlexW3016883099MaRDI QIDQ2058762
Publication date: 9 December 2021
Published in: Statistics and Computing (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2004.07177
Continuous-time Markov processes on general state spaces (60J25) Nonlinear programming (90C30) Ergodicity, mixing, rates of mixing (37A25) Numerical analysis or methods applied to Markov chains (65C40) Randomized algorithms (68W20)
Related Items (6)
Gradient flows and randomised thresholding: sparse inversion and classification* ⋮ Analysis of kinetic models for label switching and stochastic gradient descent ⋮ Bayesian Inverse Problems Are Usually Well-Posed ⋮ Subsampling in ensemble Kalman inversion ⋮ Stochastic gradient descent with noise of machine learning type. II: Continuous time analysis ⋮ Data assimilation -- mathematical foundation and applications. Abstracts from the workshop held February 20--26, 2022
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- The Zig-Zag Process and Super-Efficient Sampling for Bayesian Analysis of Big Data
- Self-adaptive congestion control for multiclass intermittent connections in a communication network
- Qualitative properties of certain piecewise deterministic Markov processes
- Minimizing finite sums with the stochastic average gradient
- Incremental proximal methods for large scale convex optimization
- Quantitative ergodicity for some switched dynamical systems
- Method of Lyapunov functions for analysis of absorption and explosion in Markov chains
- Hybrid switching diffusions. Properties and applications
- Continuous-time Markov chains. An applications-oriented approach
- Über die analytischen Methoden in der Wahrscheinlichkeitsrechnung
- Convergence of the simulated annealing algorithm for continuous global optimization
- Piecewise deterministic Markov processes for continuous-time Monte Carlo
- On the diffusion approximation of nonconvex stochastic gradient descent
- Optimal mixed strategies in stochastic environments
- Generalized parallel tempering on Bayesian inverse problems
- Bridging the gap between constant step size stochastic gradient descent and Markov chains
- Evolutionary dynamics of competing phenotype-structured populations in periodically fluctuating environments
- Diffusion limit for the random walk Metropolis algorithm out of stationarity
- Exponential ergodicity for Markov processes with random switching
- Piecewise deterministic processes in biological models
- An Introduction to Computational Stochastic PDEs
- Invariant densities for dynamical systems with random switching
- Continuum Limits of Posteriors in Graph Bayesian Inverse Problems
- Multilevel Monte Carlo Path Simulation
- Stationary distributions for piecewise-deterministic Markov processes
- Robust Stochastic Approximation Approach to Stochastic Programming
- Stochastic Gradient Descent in Continuous Time
- Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications
- On the Infinite Swapping Limit for Parallel Tempering
- Strong error analysis for stochastic gradient descent optimization algorithms
- Stochastic Gradient Descent in Continuous Time: A Central Limit Theorem
- Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
- Analysis of the Ensemble Kalman Filter for Inverse Problems
- Approximation methods for piecewise deterministic Markov processes and their costs
- A Stochastic Approximation Method
- Optimal Transport
- Statistical mechanics.
This page was built for publication: Analysis of stochastic gradient descent in continuous time
