From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
원문 초록
Biological and artificial neural networks develop internal representations that enable them to perform complex tasks. In artificial networks, the effectiveness of these models relies on their ability to build task specific representation, a process influenced by interactions among datasets, architectures, initialization strategies, and optimization algorithms. Prior studies highlight that different initializations can place networks in either a lazy regime, where representations remain static, or a rich/feature learning regime, where representations evolve dynamically. Here, we examine how initialization influences learning dynamics in deep linear neural networks, deriving exact solutions for lambda-balanced initializations-defined by the relative scale of weights across layers. These solutions capture the evolution of representations and the Neural Tangent Kernel across the spectrum from the rich to the lazy regimes. Our findings deepen the theoretical understanding of the impact of weight initialization on learning regimes, with implications for continual learning, reversal learning, and transfer learning, relevant to both neuroscience and practical applications.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
Knowledge Grafting of Large Language Models
The Bayesian Approach to Continual Learning: An Overview
BIRD: Behavior Induction via Representation-structure Distillation
Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
RaMen: Multi-Strategy Multi-Modal Learning for Bundle Construction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.