Image de couverture de livre

Geometry and convergence of natural policy gradient methods

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Müller, Johannes, Montúfar, Guido
Format:	Preprint
Publié:	2022
Sujets:	Optimization and Control Machine Learning Systems and Control 90C40, 53B12, 90C53
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients
par: Müller, Johannes, et autres
Publié: (2024)

Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes
par: Müller, Johannes, et autres
Publié: (2024)

A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces
par: Kerimkulov, Bekzhan, et autres
Publié: (2023)

SPIRAL: A superlinearly convergent incremental proximal algorithm for nonconvex finite sum minimization
par: Behmandpoor, Pourya, et autres
Publié: (2022)

Safeguarding adaptive methods: global convergence of Barzilai-Borwein and other stepsize choices
par: Ou, Hongjia, et autres
Publié: (2024)

Quasi-Newton methods for minimizing a quadratic function subject to uncertainty
par: Peng, Shen, et autres
Publié: (2021)

Nonsmooth exact penalty methods for equality-constrained optimization: complexity and implementation
par: Diouane, Youssef, et autres
Publié: (2024)

Soft quasi-Newton: Guaranteed positive definiteness by relaxing the secant constraint
par: Berglund, Erik, et autres
Publié: (2024)

Proximal Quasi-Newton Method for Composite Optimization over the Stiefel Manifold
par: Wang, Qinsi, et autres
Publié: (2025)

Novel Limited Memory Quasi-Newton Methods Based On Optimal Matrix Approximation
par: Berglund, Erik, et autres
Publié: (2024)

Riemannian Interior Point Methods for Constrained Optimization on Manifolds
par: Lai, Zhijian, et autres
Publié: (2022)

A new envelope function for nonsmooth DC optimization
par: Themelis, Andreas, et autres
Publié: (2020)

(Adaptive) Scaled gradient methods beyond locally Holder smoothness: Lyapunov analysis, convergence rate and complexity
par: Ghaderi, Susan, et autres
Publié: (2025)

Alternating Iteratively Reweighted $\ell_1$ and Subspace Newton Algorithms for Nonconvex Sparse Optimization
par: Wang, Hao, et autres
Publié: (2024)

Improving Quasi-Newton Methods via Image and Projection Operators
par: Ji, Zhenyuan
Publié: (2025)

A Stochastic Quasi-Newton Method in the Absence of Common Random Numbers
par: Menickelly, Matt, et autres
Publié: (2023)

Riemannian Gradient Method with Momentum
par: Leggio, Filippo, et autres
Publié: (2026)

A non-monotone trust-region method with noisy oracles and additional sampling
par: Krejic, Natasa, et autres
Publié: (2023)

Lipschitz upper semicontinuity of linear inequality systems under full perturbations
par: Camacho, Jesús, et autres
Publié: (2025)

A linesearch-type normal map-based semismooth Newton method for nonsmooth nonconvex composite optimization
par: Zeng, Hanfeng, et autres
Publié: (2026)

Block-coordinate and incremental aggregated proximal gradient methods for nonsmooth nonconvex problems
par: Latafat, Puya, et autres
Publié: (2019)

Nonmonotone subgradient methods based on a local descent lemma
par: Aragón-Artacho, Francisco J., et autres
Publié: (2025)

Foundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations
par: Ghojogh, Benyamin
Publié: (2026)

Modified limited memory BFGS with displacement aggregation and its application to the largest eigenvalue problem
par: Sahu, Manish Kumar, et autres
Publié: (2023)

Revisiting implicit variables in mathematical optimization: simplified modeling and a numerical evidence
par: Mehlitz, Patrick
Publié: (2025)

Non-subdifferentiability optimality and mean value theorems via new relative subdifferentials
par: Thinh, Vo Duc, et autres
Publié: (2024)

Nonlinear Conjugate Gradient Methods for Optimization of Set-Valued Mappings of Finite Cardinality
par: Ghosh, Debdas, et autres
Publié: (2024)

Stability for Nash Equilibrium Problems
par: Diao, Ruoyu, et autres
Publié: (2024)

Quasi-Newton Method for Set Optimization Problems with Set-Valued Mapping Given by Finitely Many Vector-Valued Functions
par: Ghosh, Debdas, et autres
Publié: (2024)

Generalized gradient flows in Hadamard manifolds and convex optimization on entanglement polytopes
par: Hirai, Hiroshi
Publié: (2025)

A scaling characterization of nc-rank via unbounded gradient flow
par: Hirai, Hiroshi
Publié: (2025)

Robust Graph-Based Semi-Supervised Learning via $p$-Conductances
par: Robertson, Sawyer Jack, et autres
Publié: (2025)

A Riemannian quasi-Newton algorithm for optimization with Euclidean bounds
par: Baran, Mateusz, et autres
Publié: (2026)

Mixed Newton Method for Optimization in Complex Spaces
par: Yudin, Nikita, et autres
Publié: (2024)

Approximate stationarity in disjunctive optimization: concepts, qualification conditions, and application to MPCCs
par: Käming, Isabella, et autres
Publié: (2025)

A stochastic use of the Kurdyka-Lojasiewicz property: Investigation of optimization algorithms behaviours in a non-convex differentiable framework
par: Fest, Jean-Baptiste, et autres
Publié: (2023)

Proximal Limited-Memory Quasi-Newton Methods for Nonsmooth Nonconvex Optimization
par: Dahl, Simeon vom, et autres
Publié: (2026)

Variational Properties of Decomposable Functions. Part I: Strict Epi-Calculus and Applications
par: Ouyang, Wenqing, et autres
Publié: (2023)

Characterizations of the Aubin Property of the Solution Mapping for Nonlinear Semidefinite Programming
par: Chen, Liang, et autres
Publié: (2024)

Variational Properties of Decomposable Functions. Part II: Strong Second-Order Theory
par: Ouyang, Wenqing, et autres
Publié: (2023)