no code implementations • 4 Dec 2023 • Olivier Jeunen, Hitesh Sagtani, Himanshu Doi, Rasul Karimov, Neeti Pokharna, Danish Kalim, Aleksei Ustimenko, Christopher Green, Wenzhe Shi, Rishabh Mehrotra
We highlight (1) neural networks' ability to handle large training data size, user- and item-embeddings allows for more accurate models than GBDTs in this setting, and (2) because GBDTs are less reliant on specialised hardware, they can provide an equally accurate model at a lower cost.
no code implementations • 27 Jan 2021 • Rasul Karimov, Yury Malkov, Karim Iskakov, Victor Lempitsky
We have tested the memory layer on the classification, image reconstruction and relocalization problems and found that for some of those, the memory layers can provide significant speed/accuracy improvement with the high utilization of the key-value elements, while others require more careful fine-tuning and suffer from dying keys.
2 code implementations • 6 May 2020 • Max Kochurov, Rasul Karimov, Serge Kozlukov
Geoopt is a research-oriented modular open-source package for Riemannian Optimization in PyTorch.