Georgia Tech & Google Propose a Novel Discrete Variational Autoencoder for Automatically Improving Code Efficiency

In the new paper Learning to Improve Code Efficiency, a research team from the Georgia Institute of Technology and Google Research presents a novel discrete generative latent-variable model designed to help programmers identify more computationally efficient code variants, taking a step toward automating the process of code performance optimization.

ai artificial intelligence autoencoder code deep-neural-networks efficiency georgia georgia tech google machine learning machine learning & data science ml research tech technology variational autoencoders