← Search

Ivan Koryakovskiy

2 accepted papers

2023

One-Shot Model for Mixed-Precision Quantization

CVPR 2023poster

Neural network quantization is a popular approach for model compression. Modern hardware supports quantization in mixed-precision mode, which allows for greater compression rates but adds the challenging task of searching for the optimal bit width. The majority of existing searchers find a single mi…

Cited by 20SourcePDFScholar
2018

Model-Plant Mismatch Compensation Using Reinforcement Learning

RA-L 2018

Learning-based approaches are suitable for the control of systems with unknown dynamics. However, learning from scratch involves many trials with exploratory actions until a good control policy is discovered. Real robots usually cannot withstand the exploratory actions and suffer damage. This proble

Cited by 41SourceScholar