The Importance of Being Lazy: Scaling Limits of Continual Learning

• URL: http://arxiv.org/abs/2506.16884v1
• Date: Fri, 20 Jun 2025 10:12:38 GMT
• Title: The Importance of Being Lazy: Scaling Limits of Continual Learning
• Authors: Jacopo Graldi, Alessandro Breccia, Giulia Lanzillotta, Thomas Hofmann, Lorenzo Noci,
• Abstract summary: We show that increasing model width is only beneficial when it reduces the amount of feature learning, yielding more laziness.<n>We study the intricate relationship between feature learning, task non-stationarity, and forgetting, finding that high feature learning is only beneficial with highly similar tasks.
• Score: 60.97756735877614
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite recent efforts, neural networks still struggle to learn in non-stationary environments, and our understanding of catastrophic forgetting (CF) is far from complete. In this work, we perform a systematic study on the impact of model scale and the degree of feature learning in continual learning. We reconcile existing contradictory observations on scale in the literature, by differentiating between lazy and rich training regimes through a variable parameterization of the architecture. We show that increasing model width is only beneficial when it reduces the amount of feature learning, yielding more laziness. Using the framework of dynamical mean field theory, we then study the infinite width dynamics of the model in the feature learning regime and characterize CF, extending prior theoretical results limited to the lazy regime. We study the intricate relationship between feature learning, task non-stationarity, and forgetting, finding that high feature learning is only beneficial with highly similar tasks. We identify a transition modulated by task similarity where the model exits an effectively lazy regime with low forgetting to enter a rich regime with significant forgetting. Finally, our findings reveal that neural networks achieve optimal performance at a critical level of feature learning, which depends on task non-stationarity and transfers across model scales. This work provides a unified perspective on the role of scale and feature learning in continual learning.

Related papers

• How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks [2.270857464465579]
  Recent work in continual learning has highlighted the beneficial effect of resampling weights in the last layer of a neural network (zapping)<n>We investigate in detail the pattern of learning and forgetting that take place inside a convolutional neural network when trained in challenging settings.
  arXiv  Detail & Related papers  (2025-07-02T10:18:35Z)
• A ghost mechanism: An analytical model of abrupt learning [6.509233267425589]
  We show how even a one-dimensional system can exhibit abrupt learning through ghost points rather than bifurcations.<n>Our model reveals a bifurcation-free mechanism for abrupt learning and illustrates the importance of both deliberate uncertainty and redundancy in stabilizing learning dynamics.
  arXiv  Detail & Related papers  (2025-01-04T20:49:20Z)
• Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning [26.07501953088188]
  We study how unbalanced layer-specific initialization variances and learning rates determine the degree of feature learning. Our analysis reveals that they conspire to influence the learning regime through a set of conserved quantities. We provide evidence that this unbalanced rich regime drives feature learning in deep finite-width networks, promotes interpretability of early layers in CNNs, reduces the sample complexity of learning hierarchical data, and decreases the time to grokking in modular arithmetic.
  arXiv  Detail & Related papers  (2024-06-10T10:42:37Z)
• Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes [72.75421975804132]
  Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting. We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem. Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
  arXiv  Detail & Related papers  (2023-09-11T14:16:37Z)
• Loss Dynamics of Temporal Difference Reinforcement Learning [36.772501199987076]
  We study the case learning curves for temporal difference learning of a value function with linear function approximators. We study how learning dynamics and plateaus depend on feature structure, learning rate, discount factor, and reward function.
  arXiv  Detail & Related papers  (2023-07-10T18:17:50Z)
• Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient [65.08966446962845]
  offline reinforcement learning, which aims at optimizing decision-making strategies with historical data, has been extensively applied in real-life applications. We take a step by considering offline reinforcement learning with differentiable function class approximation (DFA) Most importantly, we show offline differentiable function approximation is provably efficient by analyzing the pessimistic fitted Q-learning algorithm.
  arXiv  Detail & Related papers  (2022-10-03T07:59:42Z)
• Wide Neural Networks Forget Less Catastrophically [39.907197907411266]
  We study the impact of "width" of the neural network architecture on catastrophic forgetting. We study the learning dynamics of the network from various perspectives.
  arXiv  Detail & Related papers  (2021-10-21T23:49:23Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)
• Understanding the Role of Training Regimes in Continual Learning [51.32945003239048]
  Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. We study the effect of dropout, learning rate decay, and batch size, on forming training regimes that widen the tasks' local minima.
  arXiv  Detail & Related papers  (2020-06-12T06:00:27Z)
• The large learning rate phase of deep learning: the catapult mechanism [50.23041928811575]
  We present a class of neural networks with solvable training dynamics. We find good agreement between our model's predictions and training dynamics in realistic deep learning settings. We believe our results shed light on characteristics of models trained at different learning rates.
  arXiv  Detail & Related papers  (2020-03-04T17:52:48Z)

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.