Search papers, labs, and topics across Lattice.
(Corresponding author: A. M. Alrashdi.)A. M. Alrashdi is with the Department of Electrical Engineering, College of Engineering, University of Ha’il, P.O. Box 2440, Ha’il, 81441, Saudi Arabia (e-mail: am.alrashdi@uoh.edu.sa).O. Dhifallah was with the John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA (e-mail: oussama_dhifallah@g.harvard.edu).H. Sifaou is with the Department of Electrical and Electronic Engineering, King’s College London – Strand, London WC2R 2LS – London, UK (e-mail: houssem.sifaou@kcl.ac.uk)
1
0
2
Multi-task learning's generalization boost comes from implicit regularization, effectively postponing the dreaded double descent.