352 citations · 802 across the 51 of their papers we have counts for
60 papers
Universal Decoding via the Pairwise Error Probability
Nir Elkayam, Meir Feder
We develop a theory of universal decoding built on the pairwise error probability (PEP) primitive of a companion paper. The PEP and its error spectrum are defined for an arbitrary…
One-Shot Information Theory via the Pairwise Error Probability: Lossy, Joint Source-Channel, Erasure, and Multiuser Coding
Nir Elkayam, Meir Feder
This paper extends a one-shot (finite-blocklength) information-theoretic framework built on a single primitive: the pairwise error probability (PEP) of a randomized, dither-broken…
A Pairwise-Error-Probability Framework for One-Shot Information Theory
Nir Elkayam, Meir Feder
We develop a one-shot (finite-blocklength) channel-coding framework based on the pairwise error probability (PEP) of a decoder with randomized tie-breaking. The tie-breaking rule y…
Batches Stabilize the Minimum Norm Risk in High Dimensional Overparameterized Linear Regression
Shahar Stein Ioushua, Inbar Hasidim, Ofer Shayevitz +1
Learning algorithms that divide the data into batches are prevalent in many machine-learning applications, typically offering useful trade-offs between computational efficiency and…
Beyond Ridge Regression for Distribution-Free Data
Koby Bibas, Meir Feder
In supervised batch learning, the predictive normalized maximum likelihood (pNML) has been proposed as the min-max regret solution for the distribution-free setting, where no distr…
Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection
Koby Bibas, Meir Feder, Tal Hassner
Detecting out-of-distribution (OOD) samples is vital for developing machine learning based models for critical safety systems. Common approaches for OOD detection assume access to…