Convergence of Continual Learning in Homogeneous Deep Networks

• URL: http://arxiv.org/abs/2606.30559v1
• Date: Mon, 29 Jun 2026 16:55:45 GMT
• Title: Convergence of Continual Learning in Homogeneous Deep Networks
• Abstract summary: We show that global classification generally fails, even for linear simple models.<n>We extend our analysis to continual regression, unifying the framework for projections.
• Score: 21.210131216988298
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We characterize weakly regularized continual classification in homogeneous models as sequential projections onto task margin sets. This result generalizes prior analyses restricted to either stationary (single-task) deep models or continual linear models. We show that global convergence generally fails, even for simple models linear in data but nonlinear in parameters. Nevertheless, by leveraging results from nonconvex projection theory, we identify regularity properties of homogeneous deep networks that guarantee local linear convergence under random and cyclic task sequences. Finally, we extend our analysis to continual regression, unifying the framework for homogeneous models.

Related papers

• Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis [56.442307356162864]
  We study the theoretical aspects of score-based discrete diffusion models under the Continuous Time Markov Chain (CTMC) framework.<n>We introduce a discrete-time sampling algorithm in the general state space $[S]d$ that utilizes score estimators at predefined time points.<n>Our convergence analysis employs a Girsanov-based method and establishes key properties of the discrete score function.
  arXiv  Detail & Related papers  (2024-10-03T09:07:13Z)
• Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models [2.0738462952016232]
  Methods based on functional causal models can identify a unique graph, but suffer from the curse of dimensionality or impose strong parametric assumptions.<n>We propose a novel hybrid approach for global causal discovery in observational data that leverages local causal substructures.<n>We provide theoretical guarantees for correctness and worst-case time complexities, with empirical validation on synthetic data.
  arXiv  Detail & Related papers  (2024-05-23T12:28:16Z)
• Learning Linear Causal Representations from Interventions under General Nonlinear Mixing [52.66151568785088]
  We prove strong identifiability results given unknown single-node interventions without access to the intervention targets. This is the first instance of causal identifiability from non-paired interventions for deep neural network embeddings.
  arXiv  Detail & Related papers  (2023-06-04T02:32:12Z)
• Implicit Regularization for Group Sparsity [33.487964460794764]
  We show that gradient descent over the squared regression loss, without any explicit regularization, biases towards solutions with a group sparsity structure. We analyze the gradient dynamics of the corresponding regression problem in the general noise setting and obtain minimax-optimal error rates. In the degenerate case of size-one groups, our approach gives rise to a new algorithm for sparse linear regression.
  arXiv  Detail & Related papers  (2023-01-29T20:54:03Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• Uniform Consistency in Nonparametric Mixture Models [12.382836502781258]
  We study uniform consistency in nonparametric mixture models and mixed regression models. In the case of mixed regression, we prove $L1$ convergence of the regression functions while allowing for the component regression functions to intersect arbitrarily often.
  arXiv  Detail & Related papers  (2021-08-31T17:53:52Z)
• Lower Bounds on the Generalization Error of Nonlinear Learning Models [2.1030878979833467]
  We study in this paper lower bounds for the generalization error of models derived from multi-layer neural networks, in the regime where the size of the layers is commensurate with the number of samples in the training data. We show that unbiased estimators have unacceptable performance for such nonlinear networks in this regime. We derive explicit generalization lower bounds for general biased estimators, in the cases of linear regression and of two-layered networks.
  arXiv  Detail & Related papers  (2021-03-26T20:37:54Z)
• Benign Overfitting of Constant-Stepsize SGD for Linear Regression [122.70478935214128]
  inductive biases are central in preventing overfitting empirically. This work considers this issue in arguably the most basic setting: constant-stepsize SGD for linear regression. We reflect on a number of notable differences between the algorithmic regularization afforded by (unregularized) SGD in comparison to ordinary least squares.
  arXiv  Detail & Related papers  (2021-03-23T17:15:53Z)
• Hessian Eigenspectra of More Realistic Nonlinear Models [73.31363313577941]
  We make a emphprecise characterization of the Hessian eigenspectra for a broad family of nonlinear models. Our analysis takes a step forward to identify the origin of many striking features observed in more complex machine learning models.
  arXiv  Detail & Related papers  (2021-03-02T06:59:52Z)
• Implicit Regularization in ReLU Networks with the Square Loss [56.70360094597169]
  We show that it is impossible to characterize the implicit regularization with the square loss by any explicit function of the model parameters. Our results suggest that a more general framework may be needed to understand implicit regularization for nonlinear predictors.
  arXiv  Detail & Related papers  (2020-12-09T16:48:03Z)

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.