no code implementations • 10 Jun 2022 • Mathieu Besançon, Joaquim Dias Garcia, Benoît Legat, Akshay Sharma
We introduce DiffOpt. jl, a Julia library to differentiate through the solution of optimization problems with respect to arbitrary parameters present in the objective and/or constraints.
no code implementations • 21 Mar 2022 • Sam Leroux, Pieter Simoens, Meelis Lootus, Kartik Thakore, Akshay Sharma
Deploying machine learning applications on edge devices can bring clear benefits such as improved reliability, latency and privacy but it also introduces its own set of challenges.
no code implementations • NAACL 2022 • Neha Kennard, Tim O'Gorman, Rajarshi Das, Akshay Sharma, Chhandak Bagchi, Matthew Clinton, Pranay Kumar Yelugam, Hamed Zamani, Andrew McCallum
At the foundation of scientific evaluation is the labor-intensive process of peer review.
no code implementations • 15 Oct 2021 • Akshay Sharma, Nancy Nayak, Sheetal Kalyani
The proposed method achieves $92\%$ accuracy in a channel of noise variance $10^{-6}$ with $19. 3\%$ of the brute-force method's computation.
no code implementations • 18 Nov 2020 • Akshay Sharma, Piyush Rajesh Medikeri, Yu Zhang
This problem is more challenging than partial observability in the sense that the agent is unaware of certain knowledge, in contrast to it being partially observable: the difference between known unknowns and unknown unknowns.
no code implementations • 16 Apr 2020 • Mehrdad Zakershahrak, Shashank Rao Marpally, Akshay Sharma, Ze Gong, Yu Zhang
Given this sequential process, a formulation based on goal-based MDP for generating progressive explanations is presented.