Abhinav Shrivistava

Title: Abhinav Shrivistava: Innovator in Machine Learning Model Compression

Introduction

Abhinav Shrivistava is a notable inventor based in Silver Spring, MD (US). He has made significant contributions to the field of machine learning, particularly in the area of model compression. His innovative approach aims to enhance the efficiency and effectiveness of machine-learned models.

Latest Patents

Abhinav holds a patent titled "Compression of machine-learned models via entropy penalized weight reparameterization." This patent focuses on systems and methods that learn a compressed representation of a machine-learned model, such as a neural network. The approach involves representing model parameters within a reparameterization space during the training of the model. By employing a latent-variable data compression method, the proposed system maximizes both accuracy and model compressibility in an end-to-end manner.

Career Highlights

Abhinav is currently employed at Google Inc., where he continues to push the boundaries of innovation in machine learning. His work has garnered attention for its potential to improve the performance of neural networks through advanced compression techniques. With 1 patent to his name, he is recognized as a forward-thinking inventor in his field.

Collaborations

Abhinav has collaborated with talented individuals such as Deniz Oktay and Saurabh Singh. These partnerships have contributed to the development of cutting-edge technologies and methodologies in machine learning.

Conclusion

Abhinav Shrivistava is a pioneering inventor whose work in machine learning model compression is shaping the future of artificial intelligence. His innovative patent and contributions at Google Inc. highlight his commitment to advancing technology.