REVIEW 4 cited by
Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
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
This study investigates the loss of generalization ability in neural networks, revisiting warm-starting experiments from Ash & Adams. Our empirical analysis reveals that common methods designed to enhance plasticity by maintaining trainability provide limited benefits to generalization. While reinitializing the network can be effective, it also risks losing valuable prior knowledge. To this end, we introduce the Hare & Tortoise, inspired by the brain's complementary learning system. Hare & Tortoise consists of two components: the Hare network, which rapidly adapts to new information analogously to the hippocampus, and the Tortoise network, which gradually integrates knowledge akin to the neocortex. By periodically reinitializing the Hare network to the Tortoise's weights, our method preserves plasticity while retaining general knowledge. Hare & Tortoise can effectively maintain the network's ability to generalize, which improves advanced reinforcement learning algorithms on the Atari-100k benchmark. The code is available at https://github.com/dojeon-ai/hare-tortoise.
Forward citations
Cited by 4 Pith papers
-
Relative Value Learning
A critic that learns antisymmetric value differences ∆(s_i,s_j)=V(s_i)−V(s_j) has a provably contracting Bellman operator and an unbiased advantage estimator, and PPO with this critic matches standard PPO on Atari.
-
EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes
A bias-corrected exponential moving average (BEMA) is claimed to remove the lag of standard EMA weight averaging during LLM fine-tuning, improving convergence and final performance over EMA and vanilla training.
-
A Simple Baseline for Stable and Plastic Neural Networks
RDBP combines a new activation (ReLUDown) with decaying backpropagation to achieve strong stability and plasticity on Continual ImageNet with low overhead.
-
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). Continue with ORCID to comment.