Cover Image

Towards stable training of parallel continual learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuepan, Li, Lyu, Fan, Li, Yuyang, Feng, Wei, Liu, Guangcan, Shang, Fanhua
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Elastic Multi-Gradient Descent for Parallel Continual Learning
by: Lyu, Fan, et al.
Published: (2024)

FedNSAM:Consistency of Local and Global Flatness for Federated Learning
by: Liu, Junkang, et al.
Published: (2026)

FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
by: Liu, Junkang, et al.
Published: (2026)

Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data
by: Liu, Junkang, et al.
Published: (2026)

FedMuon: Accelerating Federated Learning with Matrix Orthogonalization
by: Liu, Junkang, et al.
Published: (2025)

FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging
by: junkang, Liu, et al.
Published: (2025)

DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm
by: Liu, Junkang, et al.
Published: (2025)

FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models
by: Liu, Junkang, et al.
Published: (2025)

Toward industrial use of continual learning : new metrics proposal for class incremental learning
by: Abbas, Konaté Mohamed, et al.
Published: (2024)

Industrial Surface Defect Detection via Diffusion Generation and Asymmetric Student-Teacher Network
by: Feng, Shuo, et al.
Published: (2026)

Affect and Effect: Limitations of regularisation-based continual learning in EEG-based emotion classification
by: Peire, Nina, et al.
Published: (2026)

Local vs Global continual learning
by: Lanzillotta, Giulia, et al.
Published: (2024)

Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only
by: Xiao, Wei, et al.
Published: (2025)

Toward Student-Oriented Teacher Network Training For Knowledge Distillation
by: Dong, Chengyu, et al.
Published: (2022)

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
by: Wang, Zengzhi, et al.
Published: (2025)

CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model
by: Chiang, Shang-Hsuan, et al.
Published: (2024)

Towards Understanding the Optimization Mechanisms in Deep Learning
by: Qi, Binchuan, et al.
Published: (2025)

Context selectivity with dynamic availability enables lifelong continual learning
by: Barry, Martin, et al.
Published: (2023)

Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
by: Luo, Beier, et al.
Published: (2025)

Cross-domain Random Pre-training with Prototypes for Reinforcement Learning
by: Liu, Xin, et al.
Published: (2023)

Review learning: Real world validation of privacy preserving continual learning across medical institutions
by: Yoo, Jaesung, et al.
Published: (2022)

Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning
by: Su, Xuerui, et al.
Published: (2025)

LaTiM: Longitudinal representation learning in continuous-time models to predict disease progression
by: Zeghlache, Rachid, et al.
Published: (2024)

IKUN: Initialization to Keep snn training and generalization great with sUrrogate-stable variaNce
by: Chang, Da, et al.
Published: (2024)

Towards Robust Multi-Modal Reasoning via Model Selection
by: Liu, Xiangyan, et al.
Published: (2023)

TinySubNets: An efficient and low capacity continual learning strategy
by: Pietroń, Marcin, et al.
Published: (2024)

Discovering physical laws with parallel symbolic enumeration
by: Ruan, Kai, et al.
Published: (2024)

Forager: a lightweight testbed for continual learning with partial observability in RL
by: Tang, Steven, et al.
Published: (2026)

Task diversity produces systematic transfer but inhibits continual reinforcement learning
by: Seth, Purab, et al.
Published: (2026)

Soup to go: mitigating forgetting during continual learning with model averaging
by: Kleiman, Anat, et al.
Published: (2025)

FastODT: A tree-based framework for efficient continual learning
by: Bretsko, Daniel, et al.
Published: (2026)

DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis
by: An, Rui, et al.
Published: (2026)

Similarity-based context aware continual learning for spiking neural networks
by: Han, Bing, et al.
Published: (2024)

Adaptive multiple optimal learning factors for neural network training
by: Challagundla, Jeshwanth
Published: (2024)

Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
by: Zhou, Fan, et al.
Published: (2024)

HealSplit: Towards Self-Healing through Adversarial Distillation in Split Federated Learning
by: Xie, Yuhan, et al.
Published: (2025)

A theoretical framework for self-supervised contrastive learning for continuous dependent data
by: Marusov, Alexander, et al.
Published: (2025)

Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
by: Fan, Tianyu, et al.
Published: (2024)

Multiplicative update rules for accelerating deep learning training and increasing robustness
by: Kirtas, Manos, et al.
Published: (2023)

Graph Generative Pre-trained Transformer
by: Chen, Xiaohui, et al.
Published: (2025)