Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights

• URL: http://arxiv.org/abs/2604.17578v2
• Date: Thu, 23 Apr 2026 20:57:29 GMT
• Title: Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights
• Abstract summary: Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks.<n>Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy.<n>To explicitly model task dependency, we consider nonlinear regression tasks and propose the assumption that these tasks are dependent in such a way that the data of the current task is a nonlinear transformation of previous data.
• Score: 47.25226184852639
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy. At the heart of developing CL theory lies the challenge that the data distribution varies across tasks, and we argue that properly addressing this challenge requires understanding this variation--dependency among tasks. To explicitly model task dependency, we consider nonlinear regression tasks and propose the assumption that these tasks are dependent in such a way that the data of the current task is a nonlinear transformation of previous data. With this model and under natural assumptions, we prove statistical recovery guarantees (more specifically, bounds on estimation errors) for several CL paradigms in practical use, including experience replay with data-independent regularization and data-independent weights that balance the losses of tasks, replay with data-dependent weights, and continual learning with data-dependent regularization (e.g., knowledge distillation). To the best of our knowledge, our bounds are informative in cases where prior work gives vacuous bounds.

Related papers

• Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning [51.07663354001582]
  Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task.<n>We present a novel approach to address this challenge, focusing on the intersection of memory-based methods and regularization approaches.<n>We formulate a regularization strategy, termed Information Maximization (IM) regularizer, for memory-based continual learning methods.
  arXiv  Detail & Related papers  (2025-12-01T15:56:00Z)
• Global Convergence of Continual Learning on Non-IID Data [51.99584235667152]
  We provide a general and comprehensive theoretical analysis for continual learning of regression models.<n>We establish the almost sure convergence results of continual learning under a general data condition for the first time.
  arXiv  Detail & Related papers  (2025-03-24T10:06:07Z)
• Federated Continual Instruction Tuning [39.344583304181135]
  Federated learning (FL) has the potential to leverage all distributed data and training resources to reduce the overhead of joint training.<n>In this work, we introduce the Federated Continual Instruction Tuning (FCIT) benchmark to model this real-world challenge.
  arXiv  Detail & Related papers  (2025-03-17T07:58:06Z)
• Continual Task Learning through Adaptive Policy Self-Composition [54.95680427960524]
  CompoFormer is a structure-based continual transformer model that adaptively composes previous policies via a meta-policy network. Our experiments reveal that CompoFormer outperforms conventional continual learning (CL) methods, particularly in longer task sequences.
  arXiv  Detail & Related papers  (2024-11-18T08:20:21Z)
• One VLM to Keep it Learning: Generation and Balancing for Data-free Continual Visual Question Answering [31.025439143093585]
  Vision-Language Models (VLMs) have shown significant promise in Visual Question Answering (VQA) tasks by leveraging web-scale multimodal datasets.<n>These models often struggle with continual learning due to catastrophic forgetting when adapting to new tasks.<n>We propose the first data-free method that leverages the language generation capability of a VLM, instead of relying on external models.
  arXiv  Detail & Related papers  (2024-11-04T16:04:59Z)
• Temporal-Difference Variational Continual Learning [77.92320830700797]
  We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.<n>Our approach effectively mitigates Catastrophic Forgetting, outperforming strong Variational CL methods.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• Detecting Morphing Attacks via Continual Incremental Training [10.796380524798744]
  Recent Continual Learning (CL) paradigm may represent an effective solution to enable incremental training, even through multiple sites. We investigate the performance of different Continual Learning methods in this scenario, simulating a learning model that is updated every time a new chunk of data, even of variable size, is available. Experimental results reveal that a particular CL method, namely Learning without Forgetting (LwF), is one of the best-performing algorithms.
  arXiv  Detail & Related papers  (2023-07-27T17:48:29Z)
• Automatic Data Augmentation via Invariance-Constrained Learning [94.27081585149836]
  Underlying data structures are often exploited to improve the solution of learning tasks. Data augmentation induces these symmetries during training by applying multiple transformations to the input data. This work tackles these issues by automatically adapting the data augmentation while solving the learning task.
  arXiv  Detail & Related papers  (2022-09-29T18:11:01Z)
• Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation [4.111899441919165]
  It is necessary for the model to learn novel relational patterns with very few labeled data while avoiding catastrophic forgetting of previous task knowledge. We propose a novel method based on embedding space regularization and data augmentation. Our method generalizes to new few-shot tasks and avoids catastrophic forgetting of previous tasks by enforcing extra constraints on the relational embeddings and by adding extra relevant data in a self-supervised manner.
  arXiv  Detail & Related papers  (2022-03-04T05:19:09Z)

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.