← Search

Alexandr Katrutsa

2 accepted papers

2022

Survey on Efficient Training of Large Neural Networks

IJCAI 2022poster

Modern Deep Neural Networks (DNNs) require significant memory to store weight, activations, and other intermediate tensors during training. Hence, many models don’t fit one GPU device or can be trained using only a small per-GPU batch size. This survey provides a systematic overview of the approache…

2020

Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs

NeurIPS 2020poster

We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models. We compare it with reverse dynamic method (known in literature as “adjoint method”) to train neural ODEs on classification, density estimation and inference approximation tasks. We als…