1,721,011 research outputs found
Data-Dependent Analysis of Learning Algorithms
No full textTypeset in Computer Modern by TEX and LATEX 2ε. Except where otherwise indicated, this thesis is my own original work. The results in this thesis were produced under the supervision of Shahar Mendel-son and Bob Williamson, and partly in collaboration with Peter Bartlett. The main contribution of this thesis are two related parts. The main technical results in the first part on random subclass bounds appeared as a journal paper with Shahar Mendelson [1], and an earlier conference paper [2]. The results were discussed with my supervisors Shahar Mendelson and Bob Williamson, who gave me advice and direction. The re-sults on the data-dependent estimation of localized complexities for the Empirical Risk Minimization algorithm appeared as part of a conference paper with Peter Bartlett and Shahar Mendelson [3], and the optimality results are work in progress and contained in an unpublished manuscript with Peter Bartlett and Shahar Mendelson [4]. This second part of the thesis is based on intensive discussions and technical advice from Shaha
Empirical Minimization
No full textThis report is a summary of the paper [BM06] of Peter Bartlett and Shahar Mendelson on Empirical Mini-mization. Typical algorithms in machine learning minimize an empirical loss. This is a particular case of minimum contrast estimation in statistics. To recall the set-up, a learning algorithm is presented with a set of i.i.d
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Embeddings with a lipschitz function
No full textWe investigate a new notion of embedding of subsets of {−1, 1} n in a given normed space, in a way which preserves the structure of the given set as a class of functions on {1,..., n}. This notion is an extension of the margin parameter often used in Nonparametric Statistics. Our main result is that even when considering “small ” subsets of {−1, 1} n, the vast majority of such sets do not embed in a better way than the entire cube in any normed space that satisfies a minor structural assumption
- …
