Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Jaehoon Lee, Lechao Xiao, Samuel S. Schoenholz, Yasaman Bahri, Roman Novak, Jascha Sohl-Dickstein, Jeffrey Pennington. Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alché-Buc, Edward A. Fox, Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada. pages 8570-8581, 2019. [doi]

This author has not been identified. Look up 'Jaehoon Lee' in GoogleThis author has not been identified. Look up 'Lechao Xiao' in GoogleThis author has not been identified. Look up 'Samuel S. Schoenholz' in GoogleThis author has not been identified. Look up 'Yasaman Bahri' in GoogleThis author has not been identified. Look up 'Roman Novak' in GoogleThis author has not been identified. Look up 'Jascha Sohl-Dickstein' in GoogleThis author has not been identified. Look up 'Jeffrey Pennington' in Google

runs on WebDSL