Live briefing
Everything about Stochastic approximation
Family of iterative methods
Stochastic approximation methods are a family of iterative methods typically used for root-finding problems or for optimization problems. The recursive update rules of stochastic approximation methods can be used, among other things, for solving linear systems when the collected data is corrupted by noise, or for approximating extreme values of functions which cannot be computed directly, but only estimated via noisy observations. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Stochastic approximationA 5-minute orientation
- Skim a recent paper: Imitation learning-driven approximation of stochastic control modelsInfluential work since 2022
- Pick up a classic book: Stochastic approximationThe most-reprinted book on the subject
- Read the landmark paper: A Stochastic Approximation MethodCited 7,369 times
- Go sideways: Stochastic gradient Langevin dynamicsA closely related topic
- Go sideways: Consistent estimatorA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
A Stochastic Approximation Method
Robust Stochastic Approximation Approach to Stochastic Programming
Multidimensional Stochastic Approximation Methods
Accelerated Stochastic Approximation
On a Stochastic Approximation Method
Stochastic approximation: invited paper
Approximation in stochastic scheduling
Adaptive Design and Stochastic Approximation
🆕 Influential since 2022
Imitation learning-driven approximation of stochastic control models
Online Learning Under a Separable Stochastic Approximation Framework
Robust Approximation of the Stochastic Koopman Operator
Concentration of Contractive Stochastic Approximation and Reinforcement Learning
Annealing Optimization for Progressive Learning With Stochastic Approximation
📚 Books worth reading
Stochastic approximationVivek S. Borkar · 2008
Stochastic Algorithms: Foundations and ApplicationsKathleen Steinhöfel · 2002- 📕Discrete-event simulation of fluid stochastic Petri netsGianfranco Ciardo · 1997
- 📕Qualitative Eigenschaften und Abschätzungen stochastischer ModelleDietrich Stoyan · 1977
Approximation, probability, and related fieldsGeorge A. Anastassiou, S. T. Rachev · 1994- 📕Stochastic approximation and sequential minimization under constraintsWei-Qiu Wu · 1986
Stochastic approximation and optimization of random systemsLennart Ljung · 1992- 📕Adaptive algorithms and stochastic approximationsAlbert Benveniste · 1990
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Stochastic gradient Langevin dynamics Stochastic gradient Langevin dynamics (SGLD) is an optimization and sampling technique composed of characteristics from Stochastic gradient descent, a…
- Consistent estimator In statistics, a consistent estimator or asymptotically consistent estimator is an estimator—a rule for computing estimates of a parameter θ0—having the…
- Kicked rotator The kicked rotator, also spelled as kicked rotor, is a paradigmatic model for both Hamiltonian chaos (the study of chaos in Hamiltonian systems) and quantum…
- Local martingale In mathematics, a local martingale is a type of stochastic process, satisfying the localized version of the martingale property. Every martingale is a…
- Stein discrepancy A Stein discrepancy is a statistical divergence between two probability measures that is rooted in Stein's method. It was first formulated as a tool to…
- Exponential tilting Exponential tilting (ET), exponential twisting, or exponential change of measure (ECM) is a distribution-shifting technique used in many parts of mathematics…
- Method of moments (statistics) In statistics, the method of moments is a method of estimation of population parameters. The same principle is used to derive higher moments like skewness…
- Residue (complex analysis) In mathematics, more specifically complex analysis, the residue of a function at a point of its domain is a complex number proportional to the contour…