no code implementations • 18 Dec 2019 • Soroosh Khoram, Stephen J. Wright, Jing Li
A method often used to reduce this computational cost is quantization of the vector space and location-based encoding of the dataset vectors.
no code implementations • 18 Dec 2019 • Soroosh Khoram, Jing Li
Neural network compression methods have enabled deploying large models on emerging edge devices with little cost, by adapting already-trained models to the constraints of these devices.
no code implementations • CVPR 2018 • Jialiang Zhang, Soroosh Khoram, Jing Li
The proposed method significantly outperforms state-of-the-art methods on CPU and GPU for high dimensional nearest neighbor queries on billion-scale datasets in terms of query time and accuracy regardless of the batch size.
no code implementations • ICLR 2018 • Soroosh Khoram, Jing Li
In this paper, we propose a technique that directly minimizes both the model complexity and the changes in the loss function.
no code implementations • ICLR 2018 • Soroosh Khoram, Jing Li
The optimization problem at the core of this method iteratively uses the loss function gradient to determine an error margin for each parameter and assigns it a precision accordingly.