Название исследуемой задачи:	Post Training Quantization. Flexible continuous modification for SOTA post training quantization methods to make them lossless.
Тип научной работы:	M1P
Автор:	Седова Анна
Научный руководитель:	Жариков Илья

Abstract

Neural network quantization gives the opportunity to inference large models on resource constrained devices. Post-Training Quantization(PTQ) methods have became popular, as they are simple and fast to use. They do not require whole model retraining and use only small calibration set to calculate quantization parameters. However, these methods show significant accuracy decrease on low-bit setting. There are methods that allow to increase the accuracy of model by increasing its computational complexity. In this paper, we propose a continuous modification for these methods and find a reasonable trade-off between computational complexity and performance.

Research publications

Presentations at conferences on the topic of research

Software modules developed as part of the study

1. A python package mylib with all implementation here.
2. A code with all experiment visualisation here. Can use colab.