:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Yunxiang, Cuadrado, Nicolas Mauricio, Horváth, Samuel, Takáč, Martin
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	https://arxiv.org/abs/2403.18439
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

Enhancing Policy Gradient with the Polyak Step-Size Adaption
di: Li, Yunxiang, et al.
Pubblicazione: (2024)

FRESCO: Federated Reinforcement Energy System for Cooperative Optimization
di: Cuadrado, Nicolas Mauricio, et al.
Pubblicazione: (2024)

Knowledge Distillation from Large Language Models for Household Energy Modeling
di: Takrouri, Mohannad, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

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

Tractable Probabilistic Models for Investment Planning
di: A., Nicolas M. Cuadrado, et al.
Pubblicazione: (2025)

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

Escaping Local Optima in the Waddington Landscape: A Two-Stage TRPO-PPO Approach for Single-Cell Perturbation Analysis
di: Boabang, Francis, et al.
Pubblicazione: (2025)

SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints
di: Wagner, Dominik, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

Zero-Shot Off-Policy Learning
di: Asadulaev, Arip, et al.
Pubblicazione: (2026)

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
di: Chezhegov, Savelii, et al.
Pubblicazione: (2024)

Who to Trust? Aggregating Client Predictions in Federated Distillation
di: Kovalchuk, Viktor, et al.
Pubblicazione: (2025)

Latent Reasoning in TRMs is Secretly a Policy Improvement Operator
di: Asadulaev, Arip, et al.
Pubblicazione: (2025)

Efficient Conformal Prediction under Data Heterogeneity
di: Plassier, Vincent, et al.
Pubblicazione: (2023)

Random-reshuffled SARAH does not need a full gradient computations
di: Beznosikov, Aleksandr, et al.
Pubblicazione: (2021)

SusFL: Energy-Aware Federated Learning-based Monitoring for Sustainable Smart Farms
di: Chen, Dian, et al.
Pubblicazione: (2024)

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

Expert or not? assessing data quality in offline reinforcement learning
di: Asadulaev, Arip, et al.
Pubblicazione: (2025)

Electrical Load Forecasting in Smart Grid: A Personalized Federated Learning Approach
di: Rahman, Ratun, et al.
Pubblicazione: (2024)

The AI Data Scientist
di: Akimov, Farkhad, et al.
Pubblicazione: (2025)

From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation
di: Kotelevskii, Nikita, et al.
Pubblicazione: (2024)

ProDER: A Continual Learning Approach for Fault Prediction in Evolving Smart Grids
di: Efatinasab, Emad, et al.
Pubblicazione: (2025)

Cybersecurity Assessment of Smart Grid Exposure Using a Machine Learning Based Approach
di: Jeje, Mofe O.
Pubblicazione: (2025)

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

Vanishing Feature: Diagnosing Model Merging and Beyond
di: Qu, Xingyu, et al.
Pubblicazione: (2024)