Image de couverture de livre

Memory Constrained Dynamic Subnetwork Update for Transfer Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Quélennec, Aël, Mozharovskyi, Pavlo, Nguyen, Van-Tam, Tartaglione, Enzo
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Study of Training Dynamics for Memory-Constrained Fine-Tuning
par: Quélennec, Aël, et autres
Publié: (2025)

Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning
par: Nguyen, Le-Trung, et autres
Publié: (2025)

Activation Map Compression through Tensor Decomposition for Deep Learning
par: Nguyen, Le-Trung, et autres
Publié: (2024)

Layer Collapse Can be Induced by Unstructured Pruning
par: Liao, Zhu, et autres
Publié: (2024)

Efficient Resource-Constrained Training of Transformers via Subspace Optimization
par: Nguyen, Le-Trung, et autres
Publié: (2025)

AI-Driven Intrusion Detection Systems (IDS) on the ROAD Dataset: A Comparative Analysis for Automotive Controller Area Network (CAN)
par: Guerra, Lorenzo, et autres
Publié: (2024)

Tailoring Mixup to Data for Calibration
par: Bouniot, Quentin, et autres
Publié: (2023)

Debiasing surgeon: fantastic weights and how to find them
par: Nahon, Rémi, et autres
Publié: (2024)

Self-Supervised Learning of Graph Representations for Network Intrusion Detection
par: Guerra, Lorenzo, et autres
Publié: (2025)

Instilling Inductive Biases with Subnetworks
par: Zhang, Enyan, et autres
Publié: (2023)

Model Parallelism With Subnetwork Data Parallelism
par: Singh, Vaibhav, et autres
Publié: (2025)

Hard-Constrained Neural Networks with Physics-Embedded Architecture for Residual Dynamics Learning and Invariant Enforcement in Cyber-Physical Systems
par: Spotorno, Enzo Nicolás, et autres
Publié: (2025)

Memory-Optimized Once-For-All Network
par: Girard, Maxime, et autres
Publié: (2024)

Restyling Unsupervised Concept Based Interpretable Networks with Generative Models
par: Parekh, Jayneel, et autres
Publié: (2024)

Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
par: Chen, Feng, et autres
Publié: (2023)

Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models
par: Balashov, Andrii
Publié: (2025)

Continual Deep Learning on the Edge via Stochastic Local Competition among Subnetworks
par: Christophides, Theodoros, et autres
Publié: (2024)

Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement Learning
par: Li, Chenglin, et autres
Publié: (2024)

Data Depth as a Risk
par: Castellanos, Arturo, et autres
Publié: (2025)

Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning
par: Liu, Siyu, et autres
Publié: (2026)

Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation
par: Liu, Yi-Ling, et autres
Publié: (2026)

Weighted Ensemble Models Are Strong Continual Learners
par: Marouf, Imad Eddine, et autres
Publié: (2023)

Memory Allocation in Resource-Constrained Reinforcement Learning
par: Tamborski, Massimiliano, et autres
Publié: (2025)

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization
par: Dhayalkar, Sahil Rajesh
Publié: (2025)

FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification
par: Chen, Hui, et autres
Publié: (2024)

The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR
par: Adewuyi, Israel, et autres
Publié: (2026)

Anomaly detection using data depth: multivariate case
par: Mozharovskyi, Pavlo, et autres
Publié: (2022)

Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
par: Pattichis, Andreas, et autres
Publié: (2026)

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
par: Van Nguyen, Chien, et autres
Publié: (2026)

Discovering Knowledge-Critical Subnetworks in Pretrained Language Models
par: Bayazit, Deniz, et autres
Publié: (2023)

Continual Learning: Forget-free Winning Subnetworks for Video Representations
par: Kang, Haeyong, et autres
Publié: (2023)

Continual Learning as Computationally Constrained Reinforcement Learning
par: Kumar, Saurabh, et autres
Publié: (2023)

SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning
par: Ohib, Riyasat, et autres
Publié: (2024)

Say My Name: a Model's Bias Discovery Framework
par: Ciranni, Massimiliano, et autres
Publié: (2024)

Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data
par: Stefanski, Grzegorz, et autres
Publié: (2026)

Minimizing Collateral Damage in Activation Steering
par: Nguyen, Tam, et autres
Publié: (2026)

RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget
par: Piaseczny, Adam, et autres
Publié: (2025)

How Transformers Learn In-Context Recall Tasks? Optimality, Training Dynamics and Generalization
par: Nguyen, Quan, et autres
Publié: (2025)

Robotic Constrained Imitation Learning for the Peg Transfer Task in Fundamentals of Laparoscopic Surgery
par: Kawaharazuka, Kento, et autres
Publié: (2024)

Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers
par: Liao, Zhu, et autres
Publié: (2024)