LETI: Latency Estimation Tool and Investigation of Neural Networks inference on Mobile GPU

no code implementations • 6 Oct 2020 • Evgeny Ponomarev, Sergey Matveev, Ivan Oseledets

In this work, we consider latency approximation on mobile GPU as a data and hardware-specific problem.

Neural Architecture Search

Using Reinforcement Learning in the Algorithmic Trading Problem

1 code implementation • 26 Feb 2020 • Evgeny Ponomarev, Ivan Oseledets, Andrzej Cichocki

A system for trading the fixed volume of a financial instrument is proposed and experimentally tested; this is based on the asynchronous advantage actor-critic method with the use of several neural network architectures.

Algorithmic Trading reinforcement-learning +1

Reduced-Order Modeling of Deep Neural Networks

no code implementations • 15 Oct 2019 • Julia Gusak, Talgat Daulbaev, Evgeny Ponomarev, Andrzej Cichocki, Ivan Oseledets

We introduce a new method for speeding up the inference of deep neural networks.

MUSCO: Multi-Stage Compression of neural networks

3 code implementations • 24 Mar 2019 • Julia Gusak, Maksym Kholiavchenko, Evgeny Ponomarev, Larisa Markeeva, Ivan Oseledets, Andrzej Cichocki

The low-rank tensor approximation is very promising for the compression of deep neural networks.

Neural Network Compression