Lessons Learned Addressing Dataset Bias in Model-Based Candidate Generation at Twitter

no code implementations • 13 May 2021 • Alim Virani, Jay Baxter, Dan Shiebler, Philip Gautier, Shivam Verma, Yan Xia, Apoorv Sharma, Sumit Binnani, LinLin Chen, Chenguang Yu

Traditionally, heuristic methods are used to generate candidates for large scale recommender systems.

Recommendation Systems

StopWasting My Gradients: Practical SVRG

no code implementations • NeurIPS 2015 • Reza Harikandeh, Mohamed Osama Ahmed, Alim Virani, Mark Schmidt, Jakub Konečný, Scott Sallinen

We present and analyze several strategies for improving the performance ofstochastic variance-reduced gradient (SVRG) methods.

Stop Wasting My Gradients: Practical SVRG

no code implementations • 5 Nov 2015 • Reza Babanezhad, Mohamed Osama Ahmed, Alim Virani, Mark Schmidt, Jakub Konečný, Scott Sallinen

We present and analyze several strategies for improving the performance of stochastic variance-reduced gradient (SVRG) methods.