# Compressing Recurrent Neural Network with Tensor Train

## TL;DR

This paper introduces a method to compress RNNs using Tensor Train format, significantly reducing parameters while maintaining performance across sequence tasks.

## Contribution

The paper presents a novel application of Tensor Train decomposition to compress various RNN architectures, reducing parameters up to 40 times without performance loss.

## Key findings

- Parameter reduction up to 40 times
- Maintained performance on sequence tasks
- Applicable to multiple RNN architectures

## Abstract

Recurrent Neural Network (RNN) are a popular choice for modeling temporal and sequential tasks and achieve many state-of-the-art performance on various complex problems. However, most of the state-of-the-art RNNs have millions of parameters and require many computational resources for training and predicting new data. This paper proposes an alternative RNN model to reduce the number of parameters significantly by representing the weight parameters based on Tensor Train (TT) format. In this paper, we implement the TT-format representation for several RNN architectures such as simple RNN and Gated Recurrent Unit (GRU). We compare and evaluate our proposed RNN model with uncompressed RNN model on sequence classification and sequence prediction tasks. Our proposed RNNs with TT-format are able to preserve the performance while reducing the number of RNN parameters significantly up to 40 times smaller.