Online Learning to Rank (OLTR) methods optimize rankers based on user interactions. State-of-the-art OLTR methods are built specifically for linear models. Their approaches do not extend well to non-linear models such as neural networks. We introduce an entirely novel approach to OLTR that constructs a weighted differentiable pairwise loss after each interaction: Pairwise Differentiable Gradient Descent (PDGD). PDGD breaks away from the traditional approach that relies on interleaving or multileaving and extensive sampling of models to estimate gradients. Instead, its gradient is based on inferring preferences between document pairs from user clicks and can optimize any differentiable model. We prove that the gradient of PDGD is unbiased w.r.t. user document pair preferences. Our experiments on the largest publicly available Learning to Rank (LTR) datasets show considerable and significant improvements under all levels of interaction noise. PDGD outperforms existing OLTR methods both in terms of learning speed as well as final convergence. Furthermore, unlike previous OLTR methods, PDGD also allows for non-linear models to be optimized effectively. Our results show that using a neural network leads to even better performance at convergence than a linear model. In summary, PDGD is an efficient and unbiased OLTR approach that provides a better user experience than previously possible.

Modern search systems are based on dozens or even hundreds of ranking features. The dueling bandit gradient descent (DBGD) algorithm has been shown to effectively learn combinations of these features solely from user interactions. DBGD explores the search space by comparing a possibly improved ranker to the current production ranker. To this end, it uses interleaved comparison methods, which can infer with high sensitivity a preference between two rankings based only on interaction data. A limiting factor is that it can compare only to a single exploratory ranker.We propose an online learning to rank algorithm called multileave gradient descent (MGD) that extends DBGD to learn from so-called multileaved comparison methods that can compare a set of rankings instead of merely a pair. We show experimentally that MGD allows for better selection of candidates than DBGD without the need for more comparisons involving users. An important implication of our results is that orders of magnitude less user interaction data is required to find good rankers when multileaved comparisons are used within online learning to rank. Hence, fewer users need to be exposed to possibly inferior rankers and our method allows search engines to adapt more quickly to changes in user preferences.

Counterfactual Learning to Rank (LTR) methods optimize ranking systems using logged user interactions that contain interaction biases. Existing methods are only unbiased if users are presented with all relevant items in every ranking. There is currently no existing counterfactual unbiased LTR method for top-rankings. We introduce a novel policy-aware counterfactual estimator for LTR metrics that can account for the effect of a stochastic logging policy. We prove that the policy-aware estimator is unbiased if every relevant item has a non-zero probability to appear in the top-ranking. Our experimental results show that the performance of our estimator is not affected by the size of : for any , the policy-aware estimator reaches the same retrieval performance while learning from topfeedback as when learning from feedback on the full ranking. Lastly, we introduce novel extensions of traditional LTR methods to perform counterfactual LTR and to optimize top-metrics. Together, our contributions introduce the first policy-aware unbiased LTR approach that learns from top-feedback and optimizes top-metrics. As a result, counterfactual LTR is now applicable to the very prevalent top-ranking setting in search and recommendation.