Yahoo!

About: Yahoo! is a company organization based out in London, United Kingdom. It is known for research contribution in the topics: Population & Web search query. The organization has 26749 authors who have published 29915 publications receiving 732583 citations. The organization is also known as: Yahoo! Inc. & Maudwen-Yahoo! Inc.

Sampling Algorithms and Coresets for $\ell_p$ Regression

Abstract: The $\ell_p$ regression problem takes as input a matrix $A\in\mathbb{R}^{n\times d}$, a vector $b\in\mathbb{R}^n$, and a number $p\in[1,\infty)$, and it returns as output a number ${\cal Z}$ and a vector $x_{\text{{\sc opt}}}\in\mathbb{R}^d$ such that ${\cal Z}=\min_{x\in\mathbb{R}^d}\|Ax-b\|_p=\|Ax_{\text{{\sc opt}}}-b\|_p$. In this paper, we construct coresets and obtain an efficient two-stage sampling-based approximation algorithm for the very overconstrained ($n\gg d$) version of this classical problem, for all $p\in[1, \infty)$. The first stage of our algorithm nonuniformly samples $\hat{r}_1=O(36^p d^{\max\{p/2+1,p\}+1})$ rows of $A$ and the corresponding elements of $b$, and then it solves the $\ell_p$ regression problem on the sample; we prove this is an 8-approximation. The second stage of our algorithm uses the output of the first stage to resample $\hat{r}_1/\epsilon^2$ constraints, and then it solves the $\ell_p$ regression problem on the new sample; we prove this is a $(1+\epsilon)$-approximation. Our algorithm unifies, improves upon, and extends the existing algorithms for special cases of $\ell_p$ regression, namely, $p = 1,2$ [K. L. Clarkson, in Proceedings of the 16th Annual ACM-SIAM Symposium on Discrete Algorithms, ACM, New York, SIAM, Philadelphia, 2005, pp. 257-266; P. Drineas, M. W. Mahoney, and S. Muthukrishnan, in Proceedings of the 17th Annual ACM-SIAM Symposium on Discrete Algorithms, ACM, New York, SIAM, Philadelphia, 2006, pp. 1127-1136]. In the course of proving our result, we develop two concepts—well-conditioned bases and subspace-preserving sampling—that are of independent interest.

Systems and methods for collaborative tag suggestions

Abstract: A set of general criteria have been defined to improve the efficacy of a tagging system, and have been applied to present collaborative tag suggestions to a user The collaborative tag suggestions are based on a goodness measure for tags derived from collective user authorities to combat spam The goodness measure is iteratively adjusted by a reward-penalty algorithm during tag selection The collaborative tag suggestions can also incorporate other sources of tags, eg, content-based auto-generated tags

Changes of Peel Essential Oil Composition of Four Tunisian Citrus during Fruit Maturation

Abstract: The present work investigates the effect of ripening stage on the chemical composition of essential oil extracted from peel of four citrus: bitter orange (Citrus aurantium), lemon (Citrus limon), orange maltaise (Citrus sinensis), and mandarin (Citrus reticulate) and on their antibacterial activity. Essential oils yields varied during ripening from 0.46 to 2.70%, where mandarin was found to be the richest. Forty volatile compounds were identified. Limonene (67.90–90.95%) and 1,8-cineole (tr-14.72%) were the most represented compounds in bitter orange oil while limonene (37.63–69.71%), β-pinene (0.63–31.49%), γ-terpinene (0.04–9.96%), and p-cymene (0.23–9.84%) were the highest ones in lemon. In the case of mandarin, the predominant compounds were limonene (51.81–69.00%), 1,8-cineole (0.01–26.43%), and γ-terpinene (2.53–14.06%). However, results showed that orange peel oil was dominated mainly by limonene (81.52–86.43%) during ripening. The results showed that ripening stage influenced significantly the antibacterial activity of the oils against Staphylococcus aureus, Escherichia coli, and Pseudomonas aeruginosa. This knowledge could help establish the optimum harvest date ensuring the maximum essential oil, limonene, as well as antibacterial compounds yields of citrus.

Machine learning applications for building structural design and performance assessment: State-of-the-art review

Abstract: Machine learning models have been shown to be useful for predicting and assessing structural performance, identifying structural condition and informing preemptive and recovery decisions by extracting patterns from data collected via various sources and media. This paper presents a review of the historical development and recent advances in the application of machine learning to the area of building structural design and performance assessment. To this end, an overview of machine learning theory and the most relevant algorithms is provided with the goal of identifying problems suitable for machine learning and the appropriate models to use. The machine learning applications in building structural design and performance assessment are then reviewed in four main categories: (1) predicting structural response and performance, (2) interpreting experimental data and formulating models to predict component-level structural properties, (3) information retrieval using images and written text and (4) recognizing patterns in structural health monitoring data. The challenges of bringing machine learning into structural engineering practice are identified, and future research opportunities are discussed.

Method and system for sharing portal subscriber information in an online social network

Abstract: A method, apparatus, and system are directed towards making a user's online portal information available to members of an online social network. Portal information can include information entered by the user and information determined based on the user's online behaviors, such as frequenting a Web site, sending spam messages, and the like. The online social network enables multiple degrees of relationships among members of the online social network. At least a portion of the portal information is made accessible to at least some of the members of the online social network who have a relationship to the user. The relationship can be through a public activity available to all members and/or through a user-defined category of members, such as family, friends, business contacts, and the like. The portal information can be used to determine which relationships will be established and/or which information will be available to members.