REVIEW 8 cited by
Maintaining Plasticity in Continual Learning via Regenerative Regularization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In continual learning, plasticity refers to the ability of an agent to quickly adapt to new information. Neural networks are known to lose plasticity when processing non-stationary data streams. In this paper, we propose L2 Init, a simple approach for maintaining plasticity by incorporating in the loss function L2 regularization toward initial parameters. This is very similar to standard L2 regularization (L2), the only difference being that L2 regularizes toward the origin. L2 Init is simple to implement and requires selecting only a single hyper-parameter. The motivation for this method is the same as that of methods that reset neurons or parameter values. Intuitively, when recent losses are insensitive to particular parameters, these parameters should drift toward their initial values. This prepares parameters to adapt quickly to new tasks. On problems representative of different types of nonstationarity in continual supervised learning, we demonstrate that L2 Init most consistently mitigates plasticity loss compared to previously proposed approaches.
Forward citations
Cited by 8 Pith papers
-
Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
TeLAPA preserves behaviorally diverse policy neighborhoods in a shared latent space, improving MiniGrid continual RL transfer, revisit recovery, and retention over single-model preservation.
-
Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic Memorization
An information-theoretic 'local redundancy' is lower-bounded, via an entropy-cancellation argument, by the expected squared gradient norm on synthetic probe data, and this proxy modestly out-predicts existing plastici...
-
Weight Decay Improves Language Model Plasticity
Pretrained models trained with larger weight decay fine-tune better on downstream tasks, so the best pretraining checkpoint by loss is not always the best starting point for later training.
-
Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning
A constrained rational activation with denominator degree one larger than numerator and no constant term stabilizes high-UTD continuous control, while trading off long-term plasticity.
-
Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning
Utility-scaled partial neuron resets prevent policy collapse in long-horizon continual RL while matching or beating binary-reset and uniform-decay baselines on several benchmarks.
-
Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform
SAC plus Continual Backpropagation, trained only on real multi-track data, fine-tunes in ~15 minutes on an unseen lower-friction RoboRacer track and outperforms MAP and MPC.
-
A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control
Forget and Grow (FoG) combines decaying replay weights for old experiences with progressive critic-network expansion to improve continuous-control reinforcement learning, beating BRO, SimBa, and TD-MPC2 on most of 41 ...
-
Recovering Plasticity of Neural Networks via Soft Weight Rescaling
Soft Weight Rescaling shrinks each layer's weights toward their initialization at every step, bounding weight norms and improving plasticity and test accuracy in continual, warm-start, and single-task learning.
Discussion (0). Sign in to comment.