On the Convergence of Gradient-Like Flows with Noisy Gradient Input
From MaRDI portal
Publication:4602552
DOI10.1137/16M1105682zbMath1387.90187arXiv1611.06730OpenAlexW2952232129WikidataQ60142042 ScholiaQ60142042MaRDI QIDQ4602552
Mathias Staudigl, Panayotis Mertikopoulos
Publication date: 31 January 2018
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1611.06730
Convex programming (90C25) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Stochastic programming (90C15)
Related Items
Riemannian game dynamics, Inducing strong convergence of trajectories in dynamical systems associated to monotone inclusions with composite structure, Stochastic mirror descent dynamics and their convergence in monotone variational inequalities, Stochastic heavy ball, First-order methods for convex optimization, Hessian Barrier Algorithms for Linearly Constrained Optimization Problems, On stochastic mirror descent with interacting particles: convergence properties and variance reduction, On the Convergence of Mirror Descent beyond Stochastic Convex Programming, Learning in nonatomic games. I: Finite action spaces and population games, Large deviations and stochastic stability in population games, On Gradient-Based Learning in Continuous Games
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Primal-dual subgradient methods for convex problems
- Imitation dynamics with payoff shocks
- A continuous-time approach to online optimization
- Dynamical behavior of a stochastic forward-backward algorithm using random monotone operators
- Approaching the solving of constrained variational inequalities via penalty term-based dynamical systems
- The emergence of rational behavior in the presence of stochastic perturbations
- Criteria for recurrence and existence of invariant measures for multidimensional diffusions
- A second-order gradient-like dissipative dynamical system with Hessian-driven damping. Application to optimization and mechanics.
- Introductory lectures on convex optimization. A basic course.
- Learning in games with continuous action sets and unknown payoff functions
- The long-run behavior of the stochastic replicator dynamics
- Asymptotic pseudotrajectories and chain recurrent flows, with applications
- Optimization and dynamical systems
- Stability of regime-switching stochastic differential equations
- On damped second-order gradient systems
- On the robustness of learning in games with stochastically perturbed payoff observations
- Stochastic differential equations, backward SDEs, partial differential equations
- Long time behaviour and stationary regime of memory gradient diffusions
- Learning in Games via Reinforcement and Regularization
- The role of relative entropy in quantum information theory
- Convergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions
- Online Learning and Online Convex Optimization
- Dynamical systems and forward–backward algorithms associated with the sum of a convex subdifferential and a monotone cocoercive operator
- On the long time behavior of second order differential equations with asymptotically small dissipation
- Robust Stochastic Approximation Approach to Stochastic Programming
- Central Paths, Generalized Proximal Point Methods, and Cauchy Trajectories in Riemannian Manifolds
- Free-Steering Relaxation Methods for Problems with Strictly Convex Costs and Linear Constraints
- Variational Analysis
- Evolutionary Games and Population Dynamics
- Barrier Operators and Associated Gradient-Like Dynamical Systems for Constrained Minimization Problems
- THE HEAVY BALL WITH FRICTION METHOD, I. THE CONTINUOUS DYNAMICAL SYSTEM: GLOBAL EXPLORATION OF THE LOCAL MINIMA OF A REAL-VALUED FUNCTION BY ASYMPTOTIC ANALYSIS OF A DISSIPATIVE DYNAMICAL SYSTEM
- Distributed Stochastic Optimization via Matrix Exponential Learning
- A variational perspective on accelerated methods in optimization
- Hessian Riemannian Gradient Flows in Convex Programming
- Singular Riemannian barrier methods and gradient-projection dynamical systems for constrained optimization
- Ergodic Mirror Descent
- Convex Analysis