Work

Analytical characterization of sloppiness in neural networks: Insights from linear models

Year: 2025

Type: article

Source: Physical review. E

DOI: 10.1103/fs4g-9nsz

Authors: Jialin Mao, Itay Griniasty, Yan Sun, Mark K. Transtrum, James P. Sethna, Pratik Chaudhari

Institutions: University of Pennsylvania, Tel Aviv University, Cornell University

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funders: National Science Foundation, École Polytechnique Fédérale de Lausanne, Office of Naval Research

Awards: Collaborative Research: CPS: Medium: Data Driven Modeling and Analysis of Energy Conversion Systems -- Manifold Learning and Approximation, Collaborative Research: RI: Medium: MoDL: Occams Razor in Deep and Physical Learning, G3376155089, Emergent Behaviors of Dense Active Suspensions Under Shear, CAREER: Foundations of Small Data, CAREER: Connecting Mathematical Models Across Scales

OpenAlex ID: W7110907223

FWCI:

Cites: 31

Cited by:

Related to: