Search Results for author: Shailesh Acharya

Found 1 papers, 1 papers with code

You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling

1 code implementation18 Nov 2021 Zhanpeng Zeng, Yunyang Xiong, Sathya N. Ravi, Shailesh Acharya, Glenn Fung, Vikas Singh

In this paper, we show that a Bernoulli sampling attention mechanism based on Locality Sensitive Hashing (LSH), decreases the quadratic complexity of such models to linear.

Cannot find the paper you are looking for? You can Submit a new open access paper.