A Two-Timescale Stochastic Algorithm Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic (Q5883319): Difference between revisions

Latest revision as of 19:24, 31 July 2024

scientific article; zbMATH DE number 7669687

Language	Label	Description	Also known as
English	A Two-Timescale Stochastic Algorithm Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic	scientific article; zbMATH DE number 7669687

Statements

instance of

scholarly article

0 references

title

A Two-Timescale Stochastic Algorithm Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic (English)

0 references

0 references

0 references

0 references

0 references

SIAM Journal on Optimization

0 references

publication date

30 March 2023

0 references

full work available at URL

https://arxiv.org/abs/2007.05170

0 references

zbMATH Keywords

bilevel optimization

0 references

two-timescale stochastic approximation

0 references

actor-critic

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Q4999029

0 references

Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path

0 references

First-Order Methods in Optimization

0 references

Stochastic approximation with two time scales

0 references

Technical Note—The Equivalence of Two Mathematical Programs with Optimization Problems in the Constraints

0 references

Mathematical Programs with Optimization Problems in the Constraints

0 references

An overview of bilevel optimization

0 references

Q2934010

0 references

Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance

0 references

On bilevel programming. I: General nonlinear cases

0 references

Matrix concentration for products

0 references

Double penalty method for bilevel optimization problems

0 references

Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning

0 references

Convergence rate of linear two-time-scale stochastic approximation.

0 references

Q4558791

0 references

Mathematical Programs with Equilibrium Constraints

0 references

Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms

0 references

Q3096132

0 references

A First Order Method for Solving Convex Bilevel Optimization Problems

0 references

Q4626283

0 references

Algorithms for Reinforcement Learning

0 references

Descent approaches for quadratic bilevel programming

0 references

Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions

0 references

A penalty function approach for solving bi-level linear programs

0 references

Identifiers

DOI

10.1137/20M1387341

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:5883319

@@ Property / cites work @@
+Q4999029
@@ Property / cites work: Q4999029 / rank @@
+Normal rank
@@ Property / cites work @@
+Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
+Normal rank
@@ Property / cites work @@
+First-Order Methods in Optimization
@@ Property / cites work: First-Order Methods in Optimization / rank @@
+Normal rank
@@ Property / cites work @@
+Stochastic approximation with two time scales
@@ Property / cites work: Stochastic approximation with two time scales / rank @@
+Normal rank
@@ Property / cites work @@
+Technical Note—The Equivalence of Two Mathematical Programs with Optimization Problems in the Constraints
+Normal rank
@@ Property / cites work @@
+Mathematical Programs with Optimization Problems in the Constraints
+Normal rank
@@ Property / cites work @@
+An overview of bilevel optimization
@@ Property / cites work: An overview of bilevel optimization / rank @@
+Normal rank
@@ Property / cites work @@
+Q2934010
@@ Property / cites work: Q2934010 / rank @@
+Normal rank
@@ Property / cites work @@
+Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance
+Normal rank
@@ Property / cites work @@
+On bilevel programming. I: General nonlinear cases
+Normal rank
@@ Property / cites work @@
+Matrix concentration for products
@@ Property / cites work: Matrix concentration for products / rank @@
+Normal rank
@@ Property / cites work @@
+Double penalty method for bilevel optimization problems
+Normal rank
@@ Property / cites work @@
+Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning
+Normal rank
@@ Property / cites work @@
+Convergence rate of linear two-time-scale stochastic approximation.
+Normal rank
@@ Property / cites work @@
+Q4558791
@@ Property / cites work: Q4558791 / rank @@
+Normal rank
@@ Property / cites work @@
+Mathematical Programs with Equilibrium Constraints
+Normal rank
@@ Property / cites work @@
+Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms
+Normal rank
@@ Property / cites work @@
+Q3096132
@@ Property / cites work: Q3096132 / rank @@
+Normal rank
@@ Property / cites work @@
+A First Order Method for Solving Convex Bilevel Optimization Problems
+Normal rank
@@ Property / cites work @@
+Q4626283
@@ Property / cites work: Q4626283 / rank @@
+Normal rank
@@ Property / cites work @@
+Algorithms for Reinforcement Learning
@@ Property / cites work: Algorithms for Reinforcement Learning / rank @@
+Normal rank
@@ Property / cites work @@
+Descent approaches for quadratic bilevel programming
+Normal rank
@@ Property / cites work @@
+Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
+Normal rank
@@ Property / cites work @@
+A penalty function approach for solving bi-level linear programs
+Normal rank