Yisong Yue

A support vector method for optimizing average precision

Machine learning is commonly used to improve ranked retrieval systems. Due to computational difficulties, few learning techniques have been developed to directly optimize for mean average precision (MAP), despite its widespread use in evaluating such systems. Existing approaches optimizing MAP either do not find a globally optimal solution, or are computationally expensive. In contrast, we present a general SVM learning algorithm that efficiently finds a globally optimal solution to a straightforward relaxation of MAP. We evaluate our approach using the TREC 9 and TREC 10 Web Track corpora (WT10g), comparing against SVMs optimized for accuracy and ROCArea. In most cases we show our method to produce statistically significant improvements in MAP scores.

Interactively optimizing information retrieval systems as a dueling bandits problem

We present an on-line learning framework tailored towards real-time learning from observed user behavior in search engines and other information retrieval systems. In particular, we only require pairwise comparisons which were shown to be reliably inferred from implicit feedback (Joachims et al., 2007; Radlinski et al., 2008b). We will present an algorithm with theoretical guarantees as well as simulation results.

Large-scale validation and analysis of interleaved search evaluation

Interleaving is an increasingly popular technique for evaluating information retrieval systems based on implicit user feedback. While a number of isolated studies have analyzed how this technique agrees with conventional offline evaluation approaches and other online techniques, a complete picture of its efficiency and effectiveness is still lacking. In this paper we extend and combine the body of empirical evidence regarding interleaving, and provide a comprehensive analysis of interleaving using data from two major commercial search engines and a retrieval system for scientific literature. In particular, we analyze the agreement of interleaving with manual relevance judgments and observational implicit feedback measures, estimate the statistical efficiency of interleaving, and explore the relative performance of different interleaving variants. We also show how to learn improved credit-assignment functions for clicks that further increase the sensitivity of interleaving.

The K-armed dueling bandits problem

We study a partial-information online-learning problem where actions are restricted to noisy comparisons between pairs of strategies (also known as bandits). In contrast to conventional approaches that require the absolute reward of the chosen strategy to be quantifiable and observable, our setting assumes only that (noisy) binary feedback about the relative reward of two chosen strategies is available. This type of relative feedback is particularly appropriate in applications where absolute rewards have no natural scale or are difficult to measure (e.g., user-perceived quality of a set of retrieval results, taste of food, product attractiveness), but where pairwise comparisons are easy to make. We propose a novel regret formulation in this setting, as well as present an algorithm that achieves information-theoretically optimal regret bounds (up to a constant factor).

Predicting structured objects with support vector machines

Machine Learning today offers a broad repertoire of methods for classification and regression. But what if we need to predict complex objects like trees, orderings, or alignments? Such problems arise naturally in natural language processing, search engines, and bioinformatics. The following explores a generalization of Support Vector Machines (SVMs) for such complex prediction problems.

Dynamic ranked retrieval

We present a theoretically well-founded retrieval model for dynamically generating rankings based on interactive user feedback. Unlike conventional rankings that remain static after the query was issued, dynamic rankings allow and anticipate user activity, thus providing a way to combine the otherwise contradictory goals of result diversification and high recall. We develop a decision-theoretic framework to guide the design and evaluation of algorithms for this interactive retrieval setting. Furthermore, we propose two dynamic ranking algorithms, both of which are computationally efficient. We prove that these algorithms provide retrieval performance that is guaranteed to be at least as good as the optimal static ranking algorithm. In empirical evaluations, dynamic ranking shows substantial improvements in retrieval performance over conventional static rankings.

Learning more powerful test statistics for click-based retrieval evaluation

Interleaving experiments are an attractive methodology for evaluating retrieval functions through implicit feedback. Designed as a blind and unbiased test for eliciting a preference between two retrieval functions, an interleaved ranking of the results of two retrieval functions is presented to the users. It is then observed whether the users click more on results from one retrieval function or the other. While it was shown that such interleaving experiments reliably identify the better of the two retrieval functions, the naive approach of counting all clicks equally leads to a suboptimal test. We present new methods for learning how to score different types of clicks so that the resulting test statistic optimizes the statistical power of the experiment. This can lead to substantial savings in the amount of data required for reaching a target confidence level. Our methods are evaluated on an operational search engine over a collection of scientific articles.

Learning Fine-Grained Spatial Models for Dynamic Sports Play Prediction

We consider the problem of learning predictive models for in-game sports play prediction. Focusing on basketball, we develop models for anticipating near-future events given the current game state. We employ a latent factor modeling approach, which leads to a compact data representation that enables efficient prediction given raw spatiotemporal tracking data. We validate our approach using tracking data from the 2012-2013 NBA season, and show that our model can make accurate in-game predictions. We provide a detailed inspection of our learned factors, and show that our model is interpretable and corresponds to known intuitions of basketball game play.

Adaptive collective routing using gaussian process dynamic congestion models

We consider the problem of adaptively routing a fleet of cooperative vehicles within a road network in the presence of uncertain and dynamic congestion conditions. To tackle this problem, we first propose a Gaussian Process Dynamic Congestion Model that can effectively characterize both the dynamics and the uncertainty of congestion conditions. Our model is efficient and thus facilitates real-time adaptive routing in the face of uncertainty. Using this congestion model, we develop an efficient algorithm for non-myopic adaptive routing to minimize the collective travel time of all vehicles in the system. A key property of our approach is the ability to efficiently reason about the long-term value of exploration, which enables collectively balancing the exploration/exploitation trade-off for entire fleets of vehicles. We validate our approach based on traffic data from two large Asian cities. We show that our congestion model is effective in modeling dynamic congestion conditions. We also show that our routing algorithm generates significantly faster routes compared to standard baselines, and achieves near-optimal performance compared to an omniscient routing algorithm. We also present the results from a preliminary field study, which showcases the efficacy of our approach.

Identifying Team Style in Soccer Using Formations Learned from Spatiotemporal Tracking Data

To the trained-eye, experts can often identify a team based on their unique style of play due to their movement, passing and interactions. In this paper, we present a method which can accurately determine the identity of a team from spatiotemporal player tracking data. We do this by utilizing a formation descriptor which is found by minimizing the entropy of role-specific occupancy maps. We show how our approach is significantly better at identifying different teams compared to standard measures (i.e., Shots, passes etc.). We demonstrate the utility of our approach using an entire season of Prozone player tracking data from a top-tier professional soccer league.