Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model

Chiara Cammarota, Giulio Biroli, Stefano Sarao, Lenka Zdeborova, Florent Krzakala

Research output: Contribution to journal › Conference paper › peer-review

98 Downloads (Pure)

Original language	English
Journal	33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada
Volume	33
Early online date	13 Feb 2020
Publication status	Published - 2020

Access to Document

@article{d4673529019449bfbf0cdd6b052d7bcd,

title = "Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model",

author = "Chiara Cammarota and Giulio Biroli and Stefano Sarao and Lenka Zdeborova and Florent Krzakala",

year = "2020",

language = "English",

volume = "33",

journal = "33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada",

issn = "1049-5258",

}

TY - JOUR

T1 - Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model

AU - Cammarota, Chiara

AU - Biroli, Giulio

AU - Sarao, Stefano

AU - Zdeborova, Lenka

AU - Krzakala, Florent

PY - 2020

Y1 - 2020

M3 - Conference paper

SN - 1049-5258

VL - 33

JO - 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

JF - 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

ER -