no code implementations • 22 Oct 2021 • Simon Alford, Anshula Gandhi, Akshay Rangamani, Andrzej Banburski, Tony Wang, Sylee Dandekar, John Chin, Tomaso Poggio, Peter Chin
More specifically, we extend existing execution-guided program synthesis approaches with deductive reasoning based on function inverse semantics to enable a neural-guided bidirectional search algorithm.
no code implementations • 28 Jun 2020 • Akshay Rangamani, Lorenzo Rosasco, Tomaso Poggio
We study the average $\mbox{CV}_{loo}$ stability of kernel ridge-less regression and derive corresponding risk bounds.
no code implementations • 6 Feb 2019 • Akshay Rangamani, Nam H. Nguyen, Abhishek Kumar, Dzung Phan, Sang H. Chin, Trac. D. Tran
It has been empirically observed that the flatness of minima obtained from training deep networks seems to correlate with better generalization.
no code implementations • 14 Feb 2018 • Jacob A. Harer, Louis Y. Kim, Rebecca L. Russell, Onur Ozdemir, Leonard R. Kosta, Akshay Rangamani, Lei H. Hamilton, Gabriel I. Centeno, Jonathan R. Key, Paul M. Ellingwood, Erik Antelman, Alan Mackay, Marc W. McConley, Jeffrey M. Opper, Peter Chin, Tomo Lazovich
We then compare methods applied directly to source code with methods applied to artifacts extracted from the build process, finding that source-based models perform better.
no code implementations • 12 Aug 2017 • Akshay Rangamani, Anirbit Mukherjee, Amitabh Basu, Tejaswini Ganapathy, Ashish Arora, Sang Chin, Trac. D. Tran
This property holds independent of the loss function.