On the Stability of Growth in Structural Plasticity: Forward-Active yet Backward-Starved
cs.LG, cs.NE
Submitted: 2026-05-14
Updated: 2026-10-03
Terminology
Sources
- Nested Learning: The Illusion of Deep Learning Architectures
- Deep Rewiring: Training very sparse deep networks
- On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
- Sparse Networks from Scratch: Faster Training without Losing Performance
- PathNet: Evolution Channels Gradient Descent in Super Neural Networks
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Adam: A Method for Stochastic Optimization
- Plasticity Loss in Deep Reinforcement Learning: A Survey
- Maintaining Plasticity in Continual Learning via Regenerative Regularization
- Dynamic Sparse Training with Structured Sparsity
- Activation Function Design Sustains Plasticity in Continual Learning
- Neural networks with differentiable structure
- On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
- Online Continual Learning Without the Storage Constraint
- On the Convergence of Adam and Beyond
- Progressive Neural Networks
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- GROWN: GRow Only When Necessary for Continual Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks