Search papers, labs, and topics across Lattice.
Institut Courtois, Universit茅 de Montr茅al, Montr茅al, QC H2V 0B3, Canada, Acceleration Consortium, University of Toronto, Toronto, ON M5R 0A3, Canada
Mila1
0
3
Exploiting approximate label symmetries can significantly improve data scaling in machine learning, even when those symmetries aren't perfect.
