no code implementations • 13 Mar 2023 • Amir Shaikhha, Mathieu Huot, Shideh Hashemian
Sparse tensors are prevalent in many data-intensive applications, yet existing differentiable programming frameworks are tailored towards dense tensors.
no code implementations • 20 Dec 2022 • Amir Shaikhha, Mathieu Huot, Shabnam Ghasemirad, Andrew Fitzgibbon, Simon Peyton Jones, Dimitrios Vytiniotis
Automatic differentiation (AD) is a technique for computing the derivative of a function represented by a program.
no code implementations • 24 Dec 2021 • Amir Shaikhha, Marios Kelepeshis, Mahdi Ghorbani
Furthermore, we show that the performance of the code generated by our framework either outperforms or is on par with the state-of-the-art analytical query engines and a recent in-database machine learning framework.
no code implementations • 10 Mar 2021 • Amir Shaikhha, Mathieu Huot, Jaclyn Smith, Dan Olteanu
We developed SDQL, a statically typed language that can express relational algebra with aggregations, linear algebra, and functional collections over data such as relations and matrices using semi-ring dictionaries.
1 code implementation • 29 Dec 2020 • Ziniu Wu, Amir Shaikhha, Rong Zhu, Kai Zeng, Yuxing Han, Jingren Zhou
Recently proposed deep learning based methods largely improve the estimation accuracy but their performance can be greatly affected by data and often difficult for system deployment.
no code implementations • 10 Jan 2020 • Amir Shaikhha, Maximilian Schleich, Alexandru Ghita, Dan Olteanu
We consider the problem of training machine learning models over multi-relational data.
1 code implementation • 6 Jun 2018 • Amir Shaikhha, Andrew Fitzgibbon, Dimitrios Vytiniotis, Simon Peyton Jones, Christoph Koch
We present a system for the automatic differentiation of a higher-order functional array-processing language.