Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual Learning

• URL: http://arxiv.org/abs/2608.23889v1
• Date: Mon, 24 Aug 2026 22:55:46 GMT
• Title: Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual Learning
• Abstract summary: We study a minimal deep-learning analogue where a network is trained alternately on two Boolean label sets.<n>We find the system reduces to two dimensionless controls: the task disagreement $r$, the fraction of disagreeing labels, and the reach $T$.<n>Across 9,720 trajectories, an ANOVA confirms that $r$, $$, and $T$ dominate, while the effect of neutral-set size is negligible.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Plasticity under changing environments is central to both evolutionary biology and continual learning. Motivated by recent work on genotype--phenotype maps, we study a minimal deep-learning analogue where a network is trained alternately on two Boolean label sets, and ask which biological controls of plasticity survive the translation to gradient descent. Reinterpreting four proposed biological factors as quantities of training dynamics, we find the system reduces to two dimensionless controls: the task disagreement $r$, the fraction of disagreeing labels, and the reach $ηT$, the product of learning rate and switching period. We derive two bounds on plasticity: $r$ alone fixes an extremal geometric floor on the utopia distance, while $r$ and $ηT$ jointly bound forgetting. Across 9,720 trajectories, an ANOVA confirms that $r$, $η$, and $T$ dominate, while the effect of neutral-set size (emphasized in the biological setting) is negligible. The optimal reach itself follows an approximate inverse power law $ηT^{*}\propto r^{-1.18}$, yielding a heuristic that sets the optimal reach $ηT^*$ from the task disagreement alone. The analogy that survives is therefore dynamical rather than geometric, and our setting enables a view of plasticity through the lens of other driven systems in physics and engineering.

Related papers

• Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes [53.726365933748134]
  We analyze a negative weight drift induced by the interaction between standard losses and positively biased activation functions.<n>We characterize the sparsity-accuracy tradeoff across 79 configurations and identify a sharp accuracy cliff above $sim$70% activation sparsity.
  arXiv  Detail & Related papers  (2026-05-17T21:29:20Z)
• Non-Equilibrium Stochastic Dynamics as a Unified Framework for Insight and Repetitive Learning: A Kramers Escape Approach to Continual Learning [0.0]
  Continual learning in artificial neural networks is fundamentally limited by the stability-plasticity dilemma.<n>We show that both problems admit a common resolution within non-equilibrium statistical physics.
  arXiv  Detail & Related papers  (2026-04-05T15:42:23Z)
• Retina gap junctions support the robust perception by warping neural representational geometries along the visual hierarchy [49.52889244711062]
  We study the defense performance of retina gap junctions and their impact on the brain manifold.<n>Compared with other defense methods, the biological hybrid model is more robust and can be improved by introducing noise during training.<n>The results show that the biological hybrid model has a unique 2D decision boundary with high nonlinearity and a lower curvature of the decision boundary of the manifold.
  arXiv  Detail & Related papers  (2026-04-03T11:23:26Z)
• Isomorphic Functionalities between Ant Colony and Ensemble Learning: Part III -- Gradient Descent, Neural Plasticity, and the Emergence of Deep Intelligence [0.0]
  We prove that the fundamental learning algorithm underlying deep neural networks is mathematically isomorphic to the generational learning dynamics of ant colonies.<n>We show that neural plasticity mechanisms have direct analogs in colony-level adaptation.<n>This final isomorphism reveals that all three major paradigms of machine learning -- parallel ensembles, sequential ensembles, and gradient-based deep learning -- have direct analogs in the collective intelligence of social insects.
  arXiv  Detail & Related papers  (2026-04-03T00:59:49Z)
• The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning [62.72522261010872]
  Deep reinforcement learning (RL) suffers from plasticity loss severely due to the nature of non-stationarity.<n>We study the plasticity loss problem from the theoretical perspective of network optimization.<n>We propose Sample Weight Decay -- a lightweight method to restore gradient magnitude.
  arXiv  Detail & Related papers  (2026-04-02T11:29:46Z)
• Balancing Centralized Learning and Distributed Self-Organization: A Hybrid Model for Embodied Morphogenesis [0.0]
  We investigate how to couple a learnable brain-like'' controller to a cell-like'' Gray--Scott substrate to steer pattern formation with minimal effort.<n>A compact convolutional policy is embedded in a differentiable PyTorch reaction--diffusion simulator.
  arXiv  Detail & Related papers  (2025-11-13T09:05:27Z)
• Geometric Learning Dynamics [0.0]
  We present a unified framework for modeling learning dynamics in physical, biological, and machine learning systems.<n>The quantum regime corresponds to $alpha = 1$ and describes Schr"odinger-like dynamics that emerges from a discrete shift symmetry.<n>The efficient learning regime corresponds to $alpha = tfrac12$ and describes very fast machine learning algorithms.
  arXiv  Detail & Related papers  (2025-04-20T19:56:41Z)
• Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets [58.460298576330835]
  We study Leaky ResNets, which interpolate between ResNets and Fully-Connected nets depending on an 'effective depth'<n>We leverage this intuition to explain the emergence of a bottleneck structure, as observed in previous work.
  arXiv  Detail & Related papers  (2024-05-27T18:15:05Z)
• Learning Physical Dynamics with Subequivariant Graph Neural Networks [99.41677381754678]
  Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. Physical laws abide by symmetry, which is a vital inductive bias accounting for model generalization. Our model achieves on average over 3% enhancement in contact prediction accuracy across 8 scenarios on Physion and 2X lower rollout MSE on RigidFall.
  arXiv  Detail & Related papers  (2022-10-13T10:00:30Z)
• The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents [51.94554095091305]
  We argue for an introspective agent, which considers its own abilities in the context of its environment. Just as in nature, we hope to reframe strategy as one tool, among many, to succeed in an environment.
  arXiv  Detail & Related papers  (2022-01-02T20:14:01Z)
• Locality defeats the curse of dimensionality in convolutional teacher-student scenarios [69.2027612631023]
  We show that locality is key in determining the learning curve exponent $beta$. We conclude by proving, using a natural assumption, that performing kernel regression with a ridge that decreases with the size of the training set leads to similar learning curve exponents to those we obtain in the ridgeless case.
  arXiv  Detail & Related papers  (2021-06-16T08:27:31Z)
• Meta-Learning through Hebbian Plasticity in Random Networks [12.433600693422235]
  Lifelong learning and adaptability are two defining aspects of biological agents. Inspired by this biological mechanism, we propose a search method that only searches for synapse-specific Hebbian learning rules. We find that starting from completely random weights, the discovered Hebbian rules enable an agent to navigate a dynamical 2D-pixel environment.
  arXiv  Detail & Related papers  (2020-07-06T14:32:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.