paper-with-me

Papers

Information as Structural Alignment: A Dynamical Theory of Continual Learning

2026-04-08 · Radu Negulescu arxiv

Catastrophic forgetting is not an engineering failure. It is a mathematical consequence of storing knowledge as global parameter superposition. Existing methods, such as regularization, replay, and frozen subnetworks, add external mechanisms to a shared-parameter substrate. None derives retention from the learning dynamics themselves. This paper introduces the Informational Buildup Framework (IBF), an alternative substrate for continual learning, based on the premise that information is the achievement of structural alignment rather than stored content. In IBF, two equations govern the dynamics: a Law of Motion that drives configuration toward higher coherence, and Modification Dynamics that persistently deform the coherence landscape in response to localized discrepancies. Memory, agency, and self-correction arise from these dynamics rather than being added as separate modules. We first demonstrate the full lifecycle in a transparent two-dimensional toy model, then validate across three domains: a controlled non-stationary world, chess evaluated independently by Stockfish, and Split-CIFAR-100 with a frozen ViT encoder. Across all three, IBF achieves replay-superior retention without storing raw data. We observe near-zero forgetting on CIFAR-100 (BT = -0.004), positive backward transfer in chess (+38.5 cp), and 43% less forgetting than replay in the controlled domain. In chess, the framework achieves a mean behavioral advantage of +88.9 +/- 2.8 cp under independent evaluation, exceeding MLP and replay baselines.

📄 PDF Abstract BibTeX arXiv:2604.07108

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

COPR: Continual Human Preference Learning via Optimal Policy Regularization

2024-02-22 · Han Zhang, Lin Gui, Yu Lei, Yuanzhao Zhai 외

Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences. Given the evolving nature of human preferences, continual alignment …

Continual Learning

Dissipative Learning: A Framework for Viable Adaptive Systems

2026-01-25 · Laurent Caraffa arxiv

We propose a perspective in which learning is an intrinsically dissipative process. Forgetting and regularization are not heuristic add-ons but structural requirements for adaptive systems. Drawing on information theory,…

Distillation-Guided Structural Transfer for Continual Learning Beyond Sparse Distributed Memory

2025-12-17 · Huiyan Xue, Xuming Ran, Yaxin Li, Qi Xu 외 arxiv

Sparse neural systems are gaining traction for efficient continual learning due to their modularity and low interference. Architectures such as Sparse Distributed Memory Multi-Layer Perceptrons (SDMLP) construct task-spe…

Continual Learning

On the Limitation and Experience Replay for GNNs in Continual Learning

2023-02-07 · Junwei Su, Difan Zou, Chuan Wu

Continual learning seeks to empower models to progressively acquire information from a sequence of tasks. This approach is crucial for many real-world systems, which are dynamic and evolve over time. Recent research has …

Continual LearningIncremental LearningModel Selection

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization

2025-04-05 · Haoran Li, Jingfeng Wu, Vladimir Braverman

We study the statistical performance of a continual learning problem with two linear regression tasks in a well-specified random design setting. We consider a structural regularization algorithm that incorporates a gener…

Continual Learning