no code implementations • 25 Feb 2022 • Emmanuel Abbe, Elisabetta Cornacchia, Jan Hązła, Christopher Marquis
This paper introduces the notion of ``Initial Alignment'' (INAL) between a neural network at initialization and a target function.
no code implementations • 3 Nov 2021 • Ido Nachum, Jan Hązła, Michael Gastpar, Anatoly Khina
The celebrated Johnson--Lindenstrauss lemma answers this question for linear fully-connected neural networks (FNNs), stating that the geometry is essentially preserved.
no code implementations • 3 Nov 2021 • Elisabetta Cornacchia, Jan Hązła, Ido Nachum, Amir Yehudayoff
We study the implicit bias of ReLU neural networks trained by a variant of SGD where at each step, the label is changed with probability $p$ to a random label (label smoothing being a close variant of this procedure).
no code implementations • 12 May 2017 • Jan Hązła, Ali Jadbabaie, Elchanan Mossel, M. Amin Rahimian
We study the computations that Bayesian agents undertake when exchanging opinions over a network.