Automatic and Simultaneous Adjustment of Learning Rate and Momentum for Stochastic Gradient Descent

1 code implementation • 20 Aug 2019 • Tomer Lancewicki, Selcuk Kopru

Stochastic Gradient Descent (SGD) methods are prominent for training machine learning and deep learning models.

Semi-Supervised Learning with Auxiliary Evaluation Component for Large Scale e-Commerce Text Classification

no code implementations • WS 2018 • Mingkuan Liu, Musen Wen, Selcuk Kopru, Xianjing Liu, Alan Lu

To tackle this challenge, in this paper, we propose a semi-supervised learning method to utilize unlabeled data and user feedback signals to improve the performance of ML models.

General Classification Machine Translation +2

Neural Network based Extreme Classification and Similarity Models for Product Matching

no code implementations • NAACL 2018 • Kashif Shah, Selcuk Kopru, Jean-David Ruvini

Matching a seller listed item to an appropriate product has become a fundamental and one of the most significant step for e-commerce platforms for product based experience.

General Classification