28 citations · 48 across the 20 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.LG2021
A Johnson--Lindenstrauss Framework for Randomly Initialized CNNs
Ido Nachum, Jan Hązła, Michael Gastpar +1
How does the geometric representation of a dataset change after the application of each randomly initialized layer of a neural network? The celebrated Johnson--Lindenstrauss lemma…
cs.IT2021
Energy-limited Joint Source--Channel Coding via Analog Pulse Position Modulation
Omri Lev, Anatoly Khina
We study the problem of transmitting a source sample with minimum distortion over an infinite-bandwidth additive white Gaussian noise channel under an energy constraint. To that en…
cs.IT2021
Universal Joint Source-Channel Coding Under an Input Energy Constraint
Omri Lev, Anatoly Khina
We consider the problem of transmitting a source over an infinite-bandwidth additive white Gaussian noise channel with unknown noise level under an input energy constraint. We cons…