On the Theory of Continual Learning with Gradient Descent for Neural Networks

• URL: http://arxiv.org/abs/2510.05573v1
• Date: Tue, 07 Oct 2025 04:32:27 GMT
• Title: On the Theory of Continual Learning with Gradient Descent for Neural Networks
• Authors: Hossein Taheri, Avishek Ghosh, Arya Mazumdar,
• Abstract summary: We study the limitations of continual learning in a tractable yet representative setting.<n>Our results reveal interesting phenomena on the role of different problem parameters in the rate of forgetting.
• Score: 30.678616374316736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting the earlier ones, is a central goal of artificial intelligence. To shed light on its underlying mechanisms, we analyze the limitations of continual learning in a tractable yet representative setting. In particular, we study one-hidden-layer quadratic neural networks trained by gradient descent on an XOR cluster dataset with Gaussian noise, where different tasks correspond to different clusters with orthogonal means. Our results obtain bounds on the rate of forgetting during train and test-time in terms of the number of iterations, the sample size, the number of tasks, and the hidden-layer size. Our results reveal interesting phenomena on the role of different problem parameters in the rate of forgetting. Numerical experiments across diverse setups confirm our results, demonstrating their validity beyond the analyzed settings.

Related papers

• The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions [51.68215326304272]
  We show that even small perturbations reliably cause otherwise identical training trajectories to diverge-an effect that diminishes rapidly over training time.<n>Our findings provide insights into neural network training stability, with practical implications for fine-tuning, model merging, and diversity of model ensembles.
  arXiv  Detail & Related papers  (2025-06-16T08:35:16Z)
• On the Interpolation Effect of Score Smoothing in Diffusion Models [12.335698325757493]
  We study the hypothesis that such creativity arises from an effect caused by a smoothing of the empirical score function.<n>We show theoretically how regularized two-layer ReLU neural networks tend to learn approximately a smoothed version of the empirical score function.<n>We present experimental evidence that learning score functions with neural networks indeed induces a score smoothing effect.
  arXiv  Detail & Related papers  (2025-02-26T19:04:01Z)
• Understanding Activation Patterns in Artificial Neural Networks by Exploring Stochastic Processes [0.0]
  We propose utilizing the framework of processes, which has been underutilized thus far. We focus solely on activation frequency, leveraging neuroscience techniques used for real neuron spike trains. We derive parameters describing activation patterns in each network, revealing consistent differences across architectures and training sets.
  arXiv  Detail & Related papers  (2023-08-01T22:12:30Z)
• Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs [5.7166378791349315]
  We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network converges to zero loss. We also show and characterise a surprising distinction in this setting between interpolator networks of minimal rank and those of minimal Euclidean norm.
  arXiv  Detail & Related papers  (2023-06-10T16:36:22Z)
• Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering [58.82325933356066]
  Continual learning aims to train a model incrementally on a sequence of tasks without forgetting previous knowledge. We present a detailed study of how different settings affect performance for Visual Question Answering.
  arXiv  Detail & Related papers  (2022-09-30T19:12:58Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Multi-scale Feature Learning Dynamics: Insights for Double Descent [71.91871020059857]
  We study the phenomenon of "double descent" of the generalization error. We find that double descent can be attributed to distinct features being learned at different scales.
  arXiv  Detail & Related papers  (2021-12-06T18:17:08Z)
• Learning Curves for Sequential Training of Neural Networks: Self-Knowledge Transfer and Forgetting [9.734033555407406]
  We consider neural networks in the neural tangent kernel regime that continually learn target functions from task to task. We investigate a variant of continual learning where the model learns the same target function in multiple tasks. Even for the same target, the trained model shows some transfer and forgetting depending on the sample size of each task.
  arXiv  Detail & Related papers  (2021-12-03T00:25:01Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)
• Latent Network Structure Learning from High Dimensional Multivariate Point Processes [5.079425170410857]
  We propose a new class of nonstationary Hawkes processes to characterize the complex processes underlying the observed data. We estimate the latent network structure using an efficient sparse least squares estimation approach. We demonstrate the efficacy of our proposed method through simulation studies and an application to a neuron spike train data set.
  arXiv  Detail & Related papers  (2020-04-07T17:48:01Z)

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.