Ionut-Vlad Modoranu

According to our database, Ionut-Vlad Modoranu authored at least 6 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics.

Thomas Robert, Mher Safaryan, Ionut-Vlad Modoranu, Dan Alistarh

CoRR, 2024

The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information.

Diyuan Wu, Ionut-Vlad Modoranu, Mher Safaryan, Denis Kuznedelev, Dan Alistarh

CoRR, 2024

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence.

Ionut-Vlad Modoranu, Mher Safaryan, Grigory Malinovsky, Eldar Kurtic, Thomas Robert, Peter Richtárik, Dan Alistarh

CoRR, 2024

Error Feedback Can Accurately Compress Preconditioners.

Ionut-Vlad Modoranu, Aleksei Kalinov, Eldar Kurtic, Elias Frantar, Dan Alistarh

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Error Feedback Can Accurately Compress Preconditioners.

Ionut-Vlad Modoranu, Aleksei Kalinov, Eldar Kurtic, Dan Alistarh

CoRR, 2023

2021

A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference.

Sanghyun Hong, Yigitcan Kaya, Ionut-Vlad Modoranu, Tudor Dumitras

Proceedings of the 9th International Conference on Learning Representations, 2021