Imagen de Portada

Enhancing Policy Gradient with the Polyak Step-Size Adaption

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Yunxiang, Yuan, Rui, Fan, Chen, Schmidt, Mark, Horváth, Samuel, Gower, Robert M., Takáč, Martin
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generalized Policy Learning for Smart Grids: FL TRPO Approach
por: Li, Yunxiang, et al.
Publicado: (2024)

SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms
por: Abdukhakimov, Farshed, et al.
Publicado: (2023)

Taking the Road Less Scheduled with Adaptive Polyak Steps
por: Oikonomou, Dimitris, et al.
Publicado: (2025)

Collaborative and Efficient Personalization with Mixtures of Adaptors
por: Almansoori, Abdulla Jasem, et al.
Publicado: (2024)

Generalising Battery Control in Net-Zero Buildings via Personalised Federated RL
por: Avila, Nicolas M Cuadrado, et al.
Publicado: (2024)

FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning
por: Tastan, Nurbek, et al.
Publicado: (2024)

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
por: Zmushko, Philip, et al.
Publicado: (2024)

Byzantine-Robust Optimization under $(L_0, L_1)$-Smoothness
por: Bolatov, Arman, et al.
Publicado: (2026)

Step-Size Stability in Stochastic Optimization: A Theoretical Perspective
por: Schaipp, Fabian, et al.
Publicado: (2026)

PaDPaF: Partial Disentanglement with Partially-Federated GANs
por: Almansoori, Abdulla Jasem, et al.
Publicado: (2022)

Federated Learning Can Find Friends That Are Advantageous
por: Tupitsa, Nazarii, et al.
Publicado: (2024)

Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
por: Oikonomou, Dimitris, et al.
Publicado: (2025)

Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
por: Demidovich, Yury, et al.
Publicado: (2024)

AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Size
por: Ostroukhov, Petr, et al.
Publicado: (2024)

LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
por: Tastan, Nurbek, et al.
Publicado: (2025)

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
por: Luo, Ruichen, et al.
Publicado: (2025)

Don't Be So Positive: Negative Step Sizes in Second-Order Methods
por: Shea, Betty, et al.
Publicado: (2024)

Cutting Some Slack for SGD with Adaptive Polyak Stepsizes
por: Gower, Robert M., et al.
Publicado: (2022)

Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update
por: Almansoori, Abdulla Jasem, et al.
Publicado: (2025)

Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC
por: Almansoori, Abdulla Jasem, et al.
Publicado: (2026)

Constrained Online Convex Optimization with Polyak Feasibility Steps
por: Hutchinson, Spencer, et al.
Publicado: (2025)

Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees
por: Agafonov, Artem, et al.
Publicado: (2025)

An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants
por: Crawshaw, Michael, et al.
Publicado: (2025)

LionMuon: Alternating Spectral and Sign Descent for Efficient Training
por: Bolatov, Arman, et al.
Publicado: (2026)

Parameter-free Clipped Gradient Descent Meets Polyak
por: Takezawa, Yuki, et al.
Publicado: (2024)

Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
por: Choudhury, Sayantan, et al.
Publicado: (2024)

Towards Parameter-Free Temporal Difference Learning
por: Li, Yunxiang, et al.
Publicado: (2026)

Non-Euclidean Gradient Descent Operates at the Edge of Stability
por: Islamov, Rustem, et al.
Publicado: (2026)

Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance
por: Oikonomou, Dimitris, et al.
Publicado: (2024)

Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge
por: Abdukhakimov, Farshed, et al.
Publicado: (2025)

Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity
por: Gorbunov, Eduard, et al.
Publicado: (2024)

Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods
por: Veprikov, Andrey, et al.
Publicado: (2025)

In Search of Adam's Secret Sauce
por: Orvieto, Antonio, et al.
Publicado: (2025)

Directional Smoothness and Gradient Methods: Convergence and Adaptivity
por: Mishkin, Aaron, et al.
Publicado: (2024)

What Scalable Second-Order Information Knows for Pruning at Initialization
por: Navarrete, Ivo Gollini, et al.
Publicado: (2025)

Adaptive Step Sizes for Preconditioned Stochastic Gradient Descent
por: Köhne, Frederik, et al.
Publicado: (2023)

Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters
por: Yukhimchuk, Alexander, et al.
Publicado: (2026)

Enhancing BERT Fine-Tuning for Sentiment Analysis in Lower-Resourced Languages
por: Kubík, Jozef, et al.
Publicado: (2025)

Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region
por: Liang, Shuang, et al.
Publicado: (2025)

Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines
por: Gower, Alex
Publicado: (2025)