Search Results for author: Michael Langberg

Found 3 papers, 0 papers with code

Dynamic D2D-Assisted Federated Learning over O-RAN: Performance Analysis, MAC Scheduler, and Asymmetric User Selection

no code implementations9 Apr 2024 Payam Abdisarabshali, Kwang Taik Kim, Michael Langberg, Weifeng Su, Seyyedali Hosseinalipour

In this paper, we incorporate multi-granular system dynamics (MSDs) into FL, including (M1) dynamic wireless channel capacity, captured by a set of discrete-time events, called $\mathscr{D}$-Events, and (M2) dynamic datasets of users.

Federated Learning

Minimizing the alphabet size in codes with restricted error sets

no code implementations4 Feb 2021 Mira Gonen, Michael Langberg, Alex Sprintson

This allows us to establish bounds on the minimum alphabet size and show an advantage of non-linear codes over linear codes in a generalized setting.

Information Theory Information Theory

A Unified Framework for Approximating and Clustering Data

no code implementations7 Jun 2011 Dan Feldman, Michael Langberg

In the $k$-clustering variant, each $x\in X$ is a tuple of $k$ shapes, and $f(x)$ is the distance from $p$ to its closest shape in $x$.

Clustering PAC learning

Cannot find the paper you are looking for? You can Submit a new open access paper.