no code implementations • 18 Jan 2024 • Maximilian Egger, Rawad Bitar, Antonia Wachter-Zeh, Deniz Gündüz, Nir Weinberger
Based on this capacity estimator, a gap-elimination algorithm termed BestChanID is proposed, which is oblivious to the capacity-achieving input distribution and is guaranteed to output the DMC with the largest capacity, with a desired confidence.
no code implementations • 25 Jun 2023 • Maximilian Egger, Christoph Hofmeister, Antonia Wachter-Zeh, Rawad Bitar
Federated learning collaboratively trains a neural network on privately owned data held by several participating clients.
no code implementations • 17 Apr 2023 • Maximilian Egger, Serge Kas Hanna, Rawad Bitar
Considering this model, we construct a novel scheme that adapts both the number of workers and the computation load throughout the run-time of the algorithm.
no code implementations • 16 Dec 2022 • Luis Maßny, Christoph Hofmeister, Maximilian Egger, Rawad Bitar, Antonia Wachter-Zeh
Since the number of stragglers in practice is random and unknown a priori, tolerating a fixed number of stragglers can yield a sub-optimal computation load and can result in higher latency.
no code implementations • 4 Aug 2022 • Serge Kas Hanna, Rawad Bitar, Parimal Parag, Venkat Dasari, Salim El Rouayheb
Moreover, the results also show that the adaptive version is communication-efficient, where the amount of communication required between the master and the workers is less than that of non-adaptive versions.
no code implementations • 16 Feb 2022 • Maximilian Egger, Rawad Bitar, Antonia Wachter-Zeh, Deniz Gündüz
We consider the distributed SGD problem, where a main node distributes gradient calculations among $n$ workers.
no code implementations • 4 Feb 2021 • Lorenz Welter, Rawad Bitar, Antonia Wachter-Zeh, Eitan Yaakobi
We show an equivalence between correcting $t$-criss-cross deletions and $t$-criss-cross insertions and show that a code correcting $t$-criss-cross insertions/deletions has redundancy at least $tn + t \log n - \log(t!)$.
Information Theory Information Theory
no code implementations • 14 Jan 2021 • Rawad Bitar, Marvin Xhemrishi, Antonia Wachter-Zeh
A master server owns two private matrices $\mathbf{A}$ and $\mathbf{B}$ and hires worker nodes to help computing their multiplication.
Information Theory Information Theory
no code implementations • 25 Feb 2020 • Serge Kas Hanna, Rawad Bitar, Parimal Parag, Venkat Dasari, Salim El Rouayheb
One solution studied in the literature is to wait at each iteration for the responses of the fastest $k<n$ workers before updating the model, where $k$ is a fixed parameter.