Image de couverture de livre

Do Neural Networks Lose Plasticity in a Gradually Changing World?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Tianhui, Mou, Lili
Format:	Preprint
Publié:	2026
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

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
par: Hao, Yongchang, et autres
Publié: (2024)

Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networks
par: Hao, Yongchang, et autres
Publié: (2024)

Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
par: Hao, Yongchang, et autres
Publié: (2026)

Neural Network Plasticity and Loss Sharpness
par: Koster, Max, et autres
Publié: (2024)

Flora: Low-Rank Adapters Are Secretly Gradient Compressors
par: Hao, Yongchang, et autres
Publié: (2024)

iPINNER: An Iterative Physics-Informed Neural Network with Ensemble Kalman Filter
par: Lu, Binghang, et autres
Publié: (2025)

A Dual-View Approach to Classifying Radiology Reports by Co-Training
par: Han, Yutong, et autres
Publié: (2024)

Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing
par: Shayegh, Behzad, et autres
Publié: (2024)

Knowledge Distillation Must Account for What It Loses
par: Wang, Wenshuo
Publié: (2026)

The Boiling Frog Threshold: Criticality and Blindness in World Model-Based Anomaly Detection Under Gradual Drift
par: Hong, Zhe
Publié: (2026)

Deep Spatio-Temporal Neural Network for Air Quality Reanalysis
par: Kheder, Ammar, et autres
Publié: (2025)

Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inference
par: Schmitt, Marvin, et autres
Publié: (2023)

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
par: Shin, Baekrok, et autres
Publié: (2024)

Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs
par: Ailon, Nir, et autres
Publié: (2025)

Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley Value
par: Ma, Le, et autres
Publié: (2025)

Do Deep Neural Network Solutions Form a Star Domain?
par: Sonthalia, Ankit, et autres
Publié: (2024)

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
par: Joudaki, Amir, et autres
Publié: (2025)

Online Neural Networks for Change-Point Detection
par: Hushchyn, Mikhail, et autres
Publié: (2020)

Can We Understand Plasticity Through Neural Collapse?
par: Bonifazi, Guglielmo, et autres
Publié: (2024)

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
par: Park, Sangyeon, et autres
Publié: (2025)

A Simple Baseline for Stable and Plastic Neural Networks
par: Künzel, Étienne, et autres
Publié: (2025)

Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation
par: Ma, Yao, et autres
Publié: (2024)

Reservoir Network with Structural Plasticity for Human Activity Recognition
par: Zyarah, Abdullah M., et autres
Publié: (2025)

COLD: Causal reasOning in cLosed Daily activities
par: Joshi, Abhinav, et autres
Publié: (2024)

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
par: Zhu, Yunqin, et autres
Publié: (2026)

Integrating Attention-Enhanced LSTM and Particle Swarm Optimization for Dynamic Pricing and Replenishment Strategies in Fresh Food Supermarkets
par: Liu, Xianchen, et autres
Publié: (2025)

Let the Quantum Creep In: Designing Quantum Neural Network Models by Gradually Swapping Out Classical Components
par: Wang, Peiyong, et autres
Publié: (2024)

Contextual Thompson Sampling via Generation of Missing Data
par: Zhang, Kelly W., et autres
Publié: (2025)

Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments
par: Kim, Hyunwoo, et autres
Publié: (2025)

Ensemble Distillation for Unsupervised Constituency Parsing
par: Shayegh, Behzad, et autres
Publié: (2023)

Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
par: Bechler-Speicher, Maya, et autres
Publié: (2025)

Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning
par: Wang, Shengyuan, et autres
Publié: (2025)

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
par: Lee, Hojoon, et autres
Publié: (2024)

Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)
par: Yu, Zony, et autres
Publié: (2025)

Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
par: Omura, Motoki, et autres
Publié: (2025)

Plasticity as the Mirror of Empowerment
par: Abel, David, et autres
Publié: (2025)

Do Transformer World Models Give Better Policy Gradients?
par: Ma, Michel, et autres
Publié: (2024)

Fed-Credit: Robust Federated Learning with Credibility Management
par: Chen, Jiayan, et autres
Publié: (2024)

Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?
par: Ma, Qian, et autres
Publié: (2024)

Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
par: Shayegh, Behzad, et autres
Publié: (2024)