1.4k citations · 1.5k across the 5 of their papers we have counts for
3 papers · 1 filter
Continual Learning in Linear Classification on Separable Data
Itay Evron, Edward Moroshko, Gon Buzaglo +4
We analyze continual learning on a sequence of separable linear classification tasks with binary labels. We show theoretically that learning with weak regularization reduces to sol…
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond
Itai Kreisler, Mor Shpigel Nacson, Daniel Soudry +1
Recent research shows that when Gradient Descent (GD) is applied to neural networks, the loss almost never decreases monotonically. Instead, the loss oscillates as gradient descent…
The Role of Codeword-to-Class Assignments in Error-Correcting Codes: An Empirical Study
Itay Evron, Ophir Onn, Tamar Weiss Orzech +2
Error-correcting codes (ECC) are used to reduce multiclass classification tasks to multiple binary classification subproblems. In ECC, classes are represented by the rows of a bina…