Shahar Gottlieb — accepted AI-conference papers

2023

Automated Search for Conjectures on Mathematical Constants using Analysis of Integer Sequences

Ofir Razon, Yoav Harris, Shahar Gottlieb, Dan Carmon, Ofir David, Ido Kaminer

ICML 2023poster

The discovery of formulas involving mathematical constants such as $\pi$ and $e$ had a great impact on various fields of science and mathematics. However, such discoveries have remained scarce, relying on the intuition of mathematicians such as Ramanujan and Gauss. Recent efforts to automate such di…

Cited by 4 Source ↗PDF ↗Scholar ↗

2023

DropCompute: simple and more robust distributed synchronous training via compute variance reduction

Niv Giladi, Shahar Gottlieb, Moran Shkolnik, Asaf Karnieli, Ron Banner, Elad Hoffer +2

NeurIPS 2023poster

Background: Distributed training is essential for large scale training of deep neural networks (DNNs). The dominant methods for large scale DNN training are synchronous (e.g. All-Reduce), but these require waiting for all workers in each step. Thus, these methods are limited by the delays caused by…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗