Variance Reduction in Gradient Exploration for Online Learning to Rank

no code implementations • 10 Jun 2019 • Huazheng Wang, Sonwoo Kim, Eric McCord-Snook, Qingyun Wu, Hongning Wang

We prove that the projected gradient is an unbiased estimation of the true gradient, and show that this lower-variance gradient estimation results in significant regret reduction.

Learning-To-Rank

Efficient Exploration of Gradient Space for Online Learning to Rank

no code implementations • 18 May 2018 • Huazheng Wang, Ramsey Langley, Sonwoo Kim, Eric McCord-Snook, Hongning Wang

In this paper, we accelerate the online learning process by efficient exploration in the gradient space.

Efficient Exploration Learning-To-Rank