Copertina

Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Comte, Céline, Jonckheere, Matthieu, Sanders, Jaron, Senen-Cerda, Albert
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning Performance Optimization and Control Probability
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimization Trade-offs in Asynchronous Federated Learning: A Stochastic Networks Approach
di: Alahyane, Abdelkrim, et al.
Pubblicazione: (2026)

Optimizing Asynchronous Federated Learning: A Delicate Trade-Off Between Model-Parameter Staleness and Update Frequency
di: Alahyane, Abdelkrim, et al.
Pubblicazione: (2025)

The suboptimality ratio of projective measurements restricted to low-rank subspaces
di: Senen-Cerda, Albert
Pubblicazione: (2024)

Admission Control of Quasi-Reversible Queueing Systems: Optimization and Reinforcement Learning
di: Comte, Céline, et al.
Pubblicazione: (2025)

The Gittins Index: A Design Principle for Decision-Making Under Uncertainty
di: Scully, Ziv, et al.
Pubblicazione: (2025)

Graph-Based Product Form
di: Comte, Céline, et al.
Pubblicazione: (2025)

Decision-Epoch Matters: Unveiling its Impact on the Stability of Scheduling with Randomly Varying Connectivity
di: Soprano-Loto, Nahuel, et al.
Pubblicazione: (2024)

Queues with resetting: a perspective
di: Roy, Reshmi, et al.
Pubblicazione: (2024)

Structure Matters: Dynamic Policy Gradient
di: Klein, Sara, et al.
Pubblicazione: (2024)

Control of parallel non-observable queues: asymptotic equivalence and optimality of periodic policies
di: Anselmi, Jonatha, et al.
Pubblicazione: (2014)

Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients
di: Bruno, Stefano, et al.
Pubblicazione: (2025)

Flatness-Aware Stochastic Gradient Langevin Dynamics
di: Bruno, Stefano, et al.
Pubblicazione: (2025)

Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
di: Kassing, Sebastian, et al.
Pubblicazione: (2025)

Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise
di: Dang, Thanh, et al.
Pubblicazione: (2025)

Efficient Solving of Large Single Input Superstate Decomposable Markovian Decision Process
di: Mahjoub, Youssef Ait El, et al.
Pubblicazione: (2025)

Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
di: Hagemann, Paul, et al.
Pubblicazione: (2023)

Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels
di: Altekrüger, Fabian, et al.
Pubblicazione: (2023)

Adversarial Network Optimization under Bandit Feedback: Maximizing Utility in Non-Stationary Multi-Hop Networks
di: Dai, Yan, et al.
Pubblicazione: (2024)

Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent
di: Ziyin, Liu, et al.
Pubblicazione: (2023)

Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems
di: Sato, Kanji, et al.
Pubblicazione: (2022)

A Piecewise Lyapunov Analysis of Sub-quadratic SGD: Applications to Robust and Quantile Regression
di: Zhang, Yixuan, et al.
Pubblicazione: (2025)

Wasserstein Formulation of Reinforcement Learning. An Optimal Transport Perspective on Policy Optimization
di: Dus, Mathias
Pubblicazione: (2026)

An Online Multiobjective Policy Gradient for Long-run Average-reward Markov Decision Process
di: Misra, Rahul, et al.
Pubblicazione: (2025)

Stability of Polling Systems for a Large Class of Markovian Switching Policies
di: Avrachenkov, Konstantin, et al.
Pubblicazione: (2025)

Set Invariance with Probability One for Controlled Diffusion: Score-based Approach
di: Wang, Wenqing, et al.
Pubblicazione: (2025)

Random Walks with Traversal Costs: Variance-Aware Performance Analysis and Network Optimization
di: Le, Thao, et al.
Pubblicazione: (2026)

Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions
di: Long, Kehan, et al.
Pubblicazione: (2025)

Optimal Risk Scores for Continuous Predictors
di: Molero-Río, Cristina, et al.
Pubblicazione: (2025)

Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization
di: Bhuyan, Neelkamal, et al.
Pubblicazione: (2023)

Guarantees for Spontaneous Synchronization on Random Geometric Graphs
di: Abdalla, Pedro, et al.
Pubblicazione: (2022)

Controlled Swarm Gradient Dynamics
di: Aubert, Louison
Pubblicazione: (2026)

Policy Synthesis for Interval MDPs via Polyhedral Lyapunov Functions
di: Monir, Negar, et al.
Pubblicazione: (2026)

(Un)supervised Learning of Maximal Lyapunov Functions
di: Barreau, Matthieu, et al.
Pubblicazione: (2024)

Asynchronous Load Balancing and Auto-scaling: Mean-Field Limit and Optimal Design
di: Anselmi, Jonatha
Pubblicazione: (2022)

The Performance Of The Unadjusted Langevin Algorithm Without Smoothness Assumptions
di: Johnston, Tim, et al.
Pubblicazione: (2025)

Complexity Guarantees for Zeroth-order Methods via Exponentially-shifted Gaussian Smoothing: Mitigating Dimension-dependence and Incorporating Decision-dependence
di: Wang, Mingrui, et al.
Pubblicazione: (2026)

Lagrangian Index Policy for Restless Bandits with Average Reward
di: Avrachenkov, Konstantin, et al.
Pubblicazione: (2024)

Variance Decay Property for Filter Stability
di: Kim, Jin Won, et al.
Pubblicazione: (2023)

Backward Map for Filter Stability Analysis
di: Kim, Jin Won, et al.
Pubblicazione: (2024)

Non-Stationary Gradient Descent for Optimal Auto-Scaling in Serverless Platforms
di: Anselmi, Jonatha, et al.
Pubblicazione: (2025)