Discovering user preferences by using time entries in click-through data to improve search engine results

The search engine log files have been used to gather direct user feedback on the relevancy of the documents presented in the results page. Typically the relative position of the clicks gathered from the log files is used a proxy for the direct user feedback. In this paper we identify reasons for the incompleteness of the relative position of clicks for deciphering the user preferences. Hence, we propose the use of time spent by the user in reading through the document as indicative of user preference for a document with respect to a query. Also, we identify the issues involved in using the time measure and propose means to address them.

Two-agent cooperative search using game models with endurance-time constraints

In this article, the problem of two Unmanned Aerial Vehicles (UAVs) cooperatively searching an unknown region is addressed. The search region is discretized into hexagonal cells and each cell is assumed to possess an uncertainty value. The UAVs have to cooperatively search these cells taking limited endurance, sensor and communication range constraints into account. Due to limited endurance, the UAVs need to return to the base station for refuelling and also need to select a base station when multiple base stations are present. This article proposes a route planning algorithm that takes endurance time constraints into account and uses game theoretical strategies to reduce the uncertainty. The route planning algorithm selects only those cells that ensure the agent will return to any one of the available bases. A set of paths are formed using these cells which the game theoretical strategies use to select a path that yields maximum uncertainty reduction. We explore non-cooperative Nash, cooperative and security strategies from game theory to enhance the search effectiveness. Monte-Carlo simulations are carried out which show the superiority of the game theoretical strategies over greedy strategy for different look ahead step length paths. Within the game theoretical strategies, non-cooperative Nash and cooperative strategy perform similarly in an ideal case, but Nash strategy performs better than the cooperative strategy when the perceived information is different. We also propose a heuristic based on partitioning of the search space into sectors to reduce computational overhead without performance degradation.

Bidding Dynamics of Rational Advertisers in Sponsored Search Auctions on the Web

In this paper, we address a key problem faced by advertisers in sponsored search auctions on the web: how much to bid, given the bids of the other advertisers, so as to maximize individual payoffs? Assuming the generalized second price auction as the auction mechanism, we formulate this problem in the framework of an infinite horizon alternative-move game of advertiser bidding behavior. For a sponsored search auction involving two advertisers, we characterize all the pure strategy and mixed strategy Nash equilibria. We also prove that the bid prices will lead to a Nash equilibrium, if the advertisers follow a myopic best response bidding strategy. Following this, we investigate the bidding behavior of the advertisers if they use Q-learning. We discover empirically an interesting trend that the Q-values converge even if both the advertisers learn simultaneously.

Multi-agent Search using Voronoi partitions

This paper addresses the problem of multiagent search in an unknown environment. The agents are autonomous in nature and are equipped with necessary sensors to carry out the search operation. The uncertainty, or lack of information about the search area is known a priori as a probability density function. The agents are deployed in an optimal way so as to maximize the one step uncertainty reduction. The agents continue to deploy themselves and reduce uncertainty till the uncertainty density is reduced over the search space below a minimum acceptable level. It has been shown, using LaSalle’s invariance principle, that a distributed control law which moves each of the agents towards the centroid of its Voronoi partition, modified by the sensor range leads to single step optimal deployment. This principle is now used to devise search trajectories for the agents. The simulations were carried out in 2D space with saturation on speeds of the agents. The results show that the control strategy per step indeed moves the agents to the respective centroid and the algorithm reduces the uncertainty distribution to the required level within a few steps.

Performance of a class of multi-robot deploy and search strategies based on centroidal voronoi configurations

This article considers a class of deploy and search strategies for multi-robot systems and evaluates their performance. The application framework used is deployment of a system of autonomous mobile robots equipped with required sensors in a search space to gather information. The lack of information about the search space is modelled as an uncertainty density distribution. The agents are deployed to maximise single-step search effectiveness. The centroidal Voronoi configuration, which achieves a locally optimal deployment, forms the basis for sequential deploy and search (SDS) and combined deploy and search (CDS) strategies. Completeness results are provided for both search strategies. The deployment strategy is analysed in the presence of constraints on robot speed and limit on sensor range for the convergence of trajectories with corresponding control laws responsible for the motion of robots. SDS and CDS strategies are compared with standard greedy and random search strategies on the basis of time taken to achieve reduction in the uncertainty density below a desired level. The simulation experiments reveal several important issues related to the dependence of the relative performances of the search strategies on parameters such as the number of robots, speed of robots and their sensor range limits.

Adaptive selection of search space in look ahead orthogonal matching pursuit

Compressive Sensing theory combines the signal sampling and compression for sparse signals resulting in reduction in sampling rate and computational complexity of the measurement system. In recent years, many recovery algorithms were proposed to reconstruct the signal efficiently. Look Ahead OMP (LAOMP) is a recently proposed method which uses a look ahead strategy and performs significantly better than other greedy methods. In this paper, we propose a modification to the LAOMP algorithm to choose the look ahead parameter L adaptively, thus reducing the complexity of the algorithm, without compromising on the performance. The performance of the algorithm is evaluated through Monte Carlo simulations.

Active learning in keyword search-based data integration

The problem of scaling up data integration, such that new sources can be quickly utilized as they are discovered, remains elusive: Global schemas for integrated data are difficult to develop and expand, and schema and record matching techniques are limited by the fact that data and metadata are often under-specified and must be disambiguated by data experts. One promising approach is to avoid using a global schema, and instead to develop keyword search-based data integration-where the system lazily discovers associations enabling it to join together matches to keywords, and return ranked results. The user is expected to understand the data domain and provide feedback about answers' quality. The system generalizes such feedback to learn how to correctly integrate data. A major open challenge is that under this model, the user only sees and offers feedback on a few ``top-'' results: This result set must be carefully selected to include answers of high relevance and answers that are highly informative when feedback is given on them. Existing systems merely focus on predicting relevance, by composing the scores of various schema and record matching algorithms. In this paper, we show how to predict the uncertainty associated with a query result's score, as well as how informative feedback is on a given result. We build upon these foundations to develop an active learning approach to keyword search-based data integration, and we validate the effectiveness of our solution over real data from several very different domains.

Alternative search strategies for a BSM resonance fitting the ATLAS diboson excess

We study an s-channel resonance R as a viable candidate to fit the diboson excess reported by ATLAS. We compute the contribution of the similar to 2 TeV resonance R to semileptonic and leptonic final states at the 13 TeV LHC. To explain the absence of an excess in the semileptonic channel, we explore the possibility where the particle R decays to additional light scalars X, X or X, Y. A modified analysis strategy has been proposed to study the three-particle final state of the resonance decay and to identify decay channels of X. Associated production of R with gauge bosons has been studied in detail to identify the production mechanism of R. We construct comprehensive categories for vector and scalar beyond-standard-model particles which may play the role of particles R, X, Y and find alternate channels to fix the new couplings and search for these particles.

Content-Based Search Engines for Construction Image Databases

Images represent a valuable source of information for the construction industry. Due to technological advancements in digital imaging, the increasing use of digital cameras is leading to an ever-increasing volume of images being stored in construction image databases and thus makes it hard for engineers to retrieve useful information from them. Content-Based Search Engines are tools that utilize the rich image content and apply pattern recognition methods in order to retrieve similar images. In this paper, we illustrate several project management tasks and show how Content-Based Search Engines can facilitate automatic retrieval, and indexing of construction images in image databases.

Predictive entropy search for efficient global optimization of black-box functions

We propose a novel information-theoretic approach for Bayesian optimization called Predictive Entropy Search (PES). At each iteration, PES selects the next evaluation point that maximizes the expected information gained with respect to the global maximum. PES codifies this intractable acquisition function in terms of the expected reduction in the differential entropy of the predictive distribution. This reformulation allows PES to obtain approximations that are both more accurate and efficient than other alternatives such as Entropy Search (ES). Furthermore, PES can easily perform a fully Bayesian treatment of the model hyperparameters while ES cannot. We evaluate PES in both synthetic and real-world applications, including optimization problems in machine learning, finance, biotechnology, and robotics. We show that the increased accuracy of PES leads to significant gains in optimization performance.

World Wide Web Image Search Engines

We propose the development of a world wide web image search engine that crawls the web collecting information about the images it finds, computes the appropriate image decompositions and indices, and stores this extracted information for searches based on image content. Indexing and searching images need not require solving the image understanding problem. Instead, the general approach should be to provide an arsenal of image decompositions and discriminants that can be precomputed for images. At search time, users can select a weighted subset of these decompositions to be used for computing image similarity measurements. While this approach avoids the search-time-dependent problem of labeling what is important in images, it still holds several important problems that require further research in the area of query by image content. We briefly explore some of these problems as they pertain to shape.

Design and Emergence in the Making of American Grand Strategy

The main research question of this thesis is how do grand strategies form. Grand strategy is defined as a state's coherent and consistent pattern of behavior over a long period of time in search of an overarching goal. The political science literature usually explains the formation of grand strategies by using a planning (or design) model. In this dissertation, I use primary sources, interviews with former government officials, and historical scholarship to show that the formation of grand strategy is better understood using a model of emergent learning imported from the business world. My two case studies examine the formation of American grand strategy during the Cold War and the post-Cold War eras. The dissertation concludes that in both these strategic eras the dominating grand strategies were formed primarily by emergent learning rather than flowing from advanced designs.

VizMaps: A Bayesian Topic Modeling Based PubMed Search Interface

A common challenge that users of academic databases face is making sense of their query outputs for knowledge discovery. This is exacerbated by the size and growth of modern databases. PubMed, a central index of biomedical literature, contains over 25 million citations, and can output search results containing hundreds of thousands of citations. Under these conditions, efficient knowledge discovery requires a different data structure than a chronological list of articles. It requires a method of conveying what the important ideas are, where they are located, and how they are connected; a method of allowing users to see the underlying topical structure of their search. This paper presents VizMaps, a PubMed search interface that addresses some of these problems. Given search terms, our main backend pipeline extracts relevant words from the title and abstract, and clusters them into discovered topics using Bayesian topic models, in particular the Latent Dirichlet Allocation (LDA). It then outputs a visual, navigable map of the query results.