no code implementations • 1 May 2024 • Enrico Lopedoto, Maksim Shekhunov, Vitaly Aksenov, Kizito Salako, Tillman Weyde
Our regularizer, called DLoss, penalises differences between the model's derivatives and derivatives of the data generating function as estimated from the training data.
no code implementations • 25 Feb 2020 • Vitaly Aksenov, Dan Alistarh, Janne H. Korhonen
The ability to leverage large-scale hardware parallelism has been one of the key enablers of the accelerated recent progress in machine learning.
no code implementations • 25 Sep 2019 • Giorgi Nadiradze, Amirmojtaba Sabour, Aditya Sharma, Ilia Markov, Vitaly Aksenov, Dan Alistarh.
We prove that, under standard assumptions, SGD can converge even in this extremely loose, decentralized setting, for both convex and non-convex objectives.
1 code implementation • 5 Feb 2015 • Vitaly Aksenov, Vincent Gramoli, Petr Kuznetsov, Srivatsan Ravi, Di Shang
Designing an efficient concurrent data structure is an important challenge that is not easy to meet.
Distributed, Parallel, and Cluster Computing