Skip to content

Amirkeivan Mohtashami

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

4

Venues

3

Active years

2021–2025

Best venue rank

A*

Where they publish

Papers

4 indexed papers, newest first.

YearVenueTitleAuthors
2025ICLRCoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference.Amirkeivan Mohtashami, Matteo Pagliardini, Martin Jaggi
2023ICMLSpecial Properties of Gradient Descent with Large Learning Rates.Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
2022AISTATSMasked Training of Neural Networks with Partial Gradients.Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
2021AISTATSCritical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates.Sebastian U. Stich, Amirkeivan Mohtashami, Martin Jaggi