Domine, Clementine;
Anguita, Nicolas;
Proca, Alexandra;
Braun, Lukas;
Mediano, Pedro;
Saxe, Andrew;
(2025)
From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks.
In:
Proceedings of the ICLR 2025 Conference.
(pp. pp. 1-52).
ICLR
Preview |
Text
Domine_From Lazy to Rich. Exact Learning Dynamics in Deep Linear Networks_VoR.pdf Download (5MB) | Preview |
Abstract
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.
| Type: | Proceedings paper |
|---|---|
| Title: | From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks |
| Event: | International Conference on Learning Representations 2025 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://openreview.net/forum?id=ZXaocmXc6d |
| Language: | English |
| Additional information: | © The Authors 2025. Original content in this paper is licensed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/). |
| Keywords: | Deep learning, Learning theory, Learning Regime, Rich, Lazy |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10205845 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
