Daniil Merkulov

According to our database, Daniil Merkulov authored at least 7 papers between 2019 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2022

NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizers.

Valentin Leplat, Daniil Merkulov, Aleksandr Katrutsa, Daniel Bershatsky, Ivan V. Oseledets

CoRR, 2022

Memory-Efficient Backpropagation through Large Linear Layers.

Daniel Bershatsky, Aleksandr Mikhalev, Alexandr Katrutsa, Julia Gusak, Daniil Merkulov, Ivan V. Oseledets

CoRR, 2022

2021

Fast Line Search for Multi-Task Learning.

Andrey Filatov, Daniil Merkulov

CoRR, 2021

A New Multi-objective Approach to Optimize Irrigation Using a Crop Simulation Model and Weather History.

Mikhail Gasanov, Daniil Merkulov, Artyom Nikitin, Sergey A. Matveev, Nikita Stasenko, Anna Petrovskaia, Mariia Pukalchik, Ivan V. Oseledets

Proceedings of the Computational Science - ICCS 2021, 2021

2020

Follow the bisector: a simple method for multi-objective optimization.

Alexandr Katrutsa, Daniil Merkulov, Nurislam Tursynbek, Ivan V. Oseledets

CoRR, 2020

Stochastic gradient algorithms from ODE splitting perspective.

Daniil Merkulov, Ivan V. Oseledets

CoRR, 2020

2019

Empirical study of extreme overfitting points of neural networks.

Daniil Merkulov, Ivan V. Oseledets

CoRR, 2019