Mathematics of Continual Learning

• URL: http://arxiv.org/abs/2504.17963v1
• Date: Thu, 24 Apr 2025 22:23:41 GMT
• Title: Mathematics of Continual Learning
• Authors: Liangzu Peng, René Vidal,
• Abstract summary: Continual learning aims to solve multiple tasks presented sequentially to the learner without forgetting previously learned tasks.<n> adaptive filtering is a classic subject in signal processing with a rich history of mathematically principled methods.
• Score: 45.73704932193178
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning is an emerging subject in machine learning that aims to solve multiple tasks presented sequentially to the learner without forgetting previously learned tasks. Recently, many deep learning based approaches have been proposed for continual learning, however the mathematical foundations behind existing continual learning methods remain underdeveloped. On the other hand, adaptive filtering is a classic subject in signal processing with a rich history of mathematically principled methods. However, its role in understanding the foundations of continual learning has been underappreciated. In this tutorial, we review the basic principles behind both continual learning and adaptive filtering, and present a comparative analysis that highlights multiple connections between them. These connections allow us to enhance the mathematical foundations of continual learning based on existing results for adaptive filtering, extend adaptive filtering insights using existing continual learning methods, and discuss a few research directions for continual learning suggested by the historical developments in adaptive filtering.

Related papers

• The Bayesian Approach to Continual Learning: An Overview [4.550647089601897]
  Continual learning is an online paradigm where a learner continually accumulates knowledge from different tasks.<n>Continual need to update the learner with data arriving sequentially strikes inherent congruence between continual learning and Bayesian inference.<n>This survey inspects different settings of Bayesian continual learning, namely task-incremental learning and class-incremental learning.
  arXiv  Detail & Related papers  (2025-07-11T17:16:13Z)
• When Meta-Learning Meets Online and Continual Learning: A Survey [39.53836535326121]
  meta-learning is a data-driven approach to optimize the learning algorithm. Continual learning and online learning, both of which involve incrementally updating a model with streaming data. This paper organizes various problem settings using consistent terminology and formal descriptions.
  arXiv  Detail & Related papers  (2023-11-09T09:49:50Z)
• A Definition of Continual Reinforcement Learning [69.56273766737527]
  In a standard view of the reinforcement learning problem, an agent's goal is to efficiently identify a policy that maximizes long-term reward. Continual reinforcement learning refers to the setting in which the best agents never stop learning. We formalize the notion of agents that "never stop learning" through a new mathematical language for analyzing and cataloging agents.
  arXiv  Detail & Related papers  (2023-07-20T17:28:01Z)
• Hierarchically Structured Task-Agnostic Continual Learning [0.0]
  We take a task-agnostic view of continual learning and develop a hierarchical information-theoretic optimality principle. We propose a neural network layer, called the Mixture-of-Variational-Experts layer, that alleviates forgetting by creating a set of information processing paths. Our approach can operate in a task-agnostic way, i.e., it does not require task-specific knowledge, as is the case with many existing continual learning algorithms.
  arXiv  Detail & Related papers  (2022-11-14T19:53:15Z)
• Transferability in Deep Learning: A Survey [80.67296873915176]
  The ability to acquire and reuse knowledge is known as transferability in deep learning. We present this survey to connect different isolated areas in deep learning with their relation to transferability. We implement a benchmark and an open-source library, enabling a fair evaluation of deep learning methods in terms of transferability.
  arXiv  Detail & Related papers  (2022-01-15T15:03:17Z)
• Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning [65.06445195580622]
  Federated learning is a new paradigm that decouples data collection and model training via multi-party computation and model aggregation. We conduct a focused survey of federated learning in conjunction with other learning algorithms.
  arXiv  Detail & Related papers  (2021-02-25T15:18:13Z)
• Discussion of Ensemble Learning under the Era of Deep Learning [4.061135251278187]
  Ensemble deep learning has shown significant performances in improving the generalization of learning system. Time and space overheads for training multiple base deep learners and testing with the ensemble deep learner are far greater than that of traditional ensemble learning. An urgent problem needs to be solved is how to take the significant advantages of ensemble deep learning while reduce the required time and space overheads.
  arXiv  Detail & Related papers  (2021-01-21T01:33:23Z)
• Importance Weighted Policy Learning and Adaptation [89.46467771037054]
  We study a complementary approach which is conceptually simple, general, modular and built on top of recent improvements in off-policy learning. The framework is inspired by ideas from the probabilistic inference literature and combines robust off-policy learning with a behavior prior. Our approach achieves competitive adaptation performance on hold-out tasks compared to meta reinforcement learning baselines and can scale to complex sparse-reward scenarios.
  arXiv  Detail & Related papers  (2020-09-10T14:16:58Z)
• Meta-Learning in Neural Networks: A Survey [4.588028371034406]
  This survey describes the contemporary meta-learning landscape. We first discuss definitions of meta-learning and position it with respect to related fields. We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods.
  arXiv  Detail & Related papers  (2020-04-11T16:34:24Z)
• Revisiting Meta-Learning as Supervised Learning [69.2067288158133]
  We aim to provide a principled, unifying framework by revisiting and strengthening the connection between meta-learning and traditional supervised learning. By treating pairs of task-specific data sets and target models as (feature, label) samples, we can reduce many meta-learning algorithms to instances of supervised learning. This view not only unifies meta-learning into an intuitive and practical framework but also allows us to transfer insights from supervised learning directly to improve meta-learning.
  arXiv  Detail & Related papers  (2020-02-03T06:13:01Z)

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.