2 papers
cs.IT2022
Optimal list decoding from noisy entropy inequality
Jan Hązła
A noisy entropy inequality for boolean functions by Samorodnitsky is applied to binary codes. It is shown that a binary code that achieves capacity on the binary erasure channel ad…
cs.LG2021
Regularization by Misclassification in ReLU Neural Networks
Elisabetta Cornacchia, Jan Hązła, Ido Nachum +1
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 to a random label (label smoothing bein…