Traditional and accelerated gradient descent for neural architecture search

DOI10.1007/978-3-030-80209-7_55OpenAlexW3185420545MaRDI QIDQ2117891

Yanyan Li

Publication date: 22 March 2022

Full work available at URL: https://arxiv.org/abs/2006.15218

zbMATH Keywords

neural networksoptimal transportgradient flowsneural architecture searchsecond order dynamicssemi-discrete optimization

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Related Items (1)

Semi-discrete optimization through semi-discrete optimal transport: a framework for neural architecture search

Uses Software

• DARTS

Cites Work

• Gradient flows of the entropy for finite Markov chains
• Nonlocal-interaction equation on graphs: gradient flow structure and continuum limit

This page was built for publication: Traditional and accelerated gradient descent for neural architecture search