activity
20192024
most citedPractical Quasi-Newton Methods for Training Deep Neural Networks

39 citations · 41 across the 7 of their papers we have counts for

collaborators
Showing 2021Show all

2 papers · 1 filter

cs.GT2021

Optimal Pricing with a Single Point

Amine Allouah, Achraf Bahamou, Omar Besbes

We study the following fundamental data-driven pricing problem. How can/should a decision-maker price its product based on data at a single historical price? How valuable is such d…

cs.LG2021★ 1 cited

Kronecker-factored Quasi-Newton Methods for Deep Learning

Yi Ren, Achraf Bahamou, Donald Goldfarb

Second-order methods have the capability of accelerating optimization by using much richer curvature information than first-order methods. However, most are impractical for deep le…