Oja's algorithm for graph clustering, Markov spectral decomposition, and risk sensitive control

DOI10.1016/j.automatica.2012.05.016zbMath1310.93049OpenAlexW2049281355MaRDI QIDQ361011

Sean P. Meyn, Vivek S. Borkar

Publication date: 28 August 2013

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: http://www.sciencedirect.com/science/article/pii/S0005109812001896

zbMATH Keywords

Markov chainsstochastic approximationgraph algorithmsrisk sensitive controlmultiplicative ergodic theoryOja's algorithmspectral theory of Markov chains

Mathematics Subject Classification ID

Eigenvalue problems (93B60)

Related Items

Fundamental design principles for reinforcement learning algorithms, Distributed user profiling via spectral methods

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Markov chains and stochastic stability
• Eigenvalue bounds on convergence to stationarity for nonreversible Markov chains, with an application to the exclusion process
• Geometric bounds for eigenvalues of Markov chains
• On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix
• A simplified neuron model as a principal component analyzer
• Phase transitions and metastability in Markovian and molecular systems
• Identification of almost invariant aggregates in reversible nearly uncoupled Markov chains
• Metastability in reversible diffusion processes. I: Sharp asymptotics for capacities and exit times
• Metastability in reversible diffusion processes. II: Precise asymptotics for small eigenvalues
• \(R\)-positivity, quasi-stationary distributions and ratio limit theorems for a class of probabilistic automata
• Principal component analysis.
• Spectral theory and limit theorems for geometrically ergodic Markov processes
• Method of stochastic approximation in the determination of the largest eigenvalue of the mathematical expectation of random matrices
• A Learning Algorithm for Risk-Sensitive Cost
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• Optimal Kullback-Leibler Aggregation via Spectral Theory of Markov Chains
• Risk-Sensitive Optimal Control for Markov Decision Processes with Monotone Cost
• Q-Learning for Risk-Sensitive Control
• Metastability in stochastic dynamics of disordered mean-field models
• Asymptotic behavior of thermal nonequilibrium steady states for a driven chain of anharmonic oscillators
• A sensitivity formula for risk-sensitive cost and the actor-critic algorithm