FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W36398315> ?p ?o ?g. }

• W36398315 abstract "This thesis has two primary thrusts. The first is developing new models and algorithms for important modern and classic learning problems. The second is establishing new connections between Machine Learning and Algorithmic Game Theory. The formulation of the PAC learning model by Valiant [201] and the Statistical Learning Theory framework by Vapnik [203] have been instrumental in the development of machine learning and the design and analysis of algorithms for supervised learning. However, while extremely influential, these models do not capture or explain other important classic learning paradigms such as Clustering, nor do they capture important emerging learning paradigms such as Semi-Supervised Learning and other ways of incorporating unlabeled data in the learning process. In this thesis, we develop the first analog of these general discriminative models to the problems of Semi-Supervised Learning and Clustering, and we analyze both their algorithmic and sample complexity implications. We also provide the first generalization of the well-established theory of learning with kernel functions to case of general pairwise similarity functions and in addition provide new positive theoretical results for Active Learning Finally, this dissertation presents new applications of techniques from Machine Learning to Algorithmic Game Theory, which has been a major area of research at the intersection of Computer Science and Economics. In machine learning, there has been growing interest in using unlabeled data together with labeled data due to the availability of large amounts of unlabeled data in many contemporary applications. As a result, a number of different semi-supervised learning methods such as Co-training, transductive SVM, or graph based methods have been developed. However, the underlying assumptions of these methods are often quite distinct and not captured by standard theoretical models. This thesis introduces a new discriminative model (a PAC or Statistical Learning Theory style model) for semi-supervised learning, that can be used to reason about many of the different approaches taken over the past decade in the Machine Learning community. This model provides a unified framework for analyzing when and why unlabeled data can help in the semi-supervised learning setting, in which one can analyze both sample-complexity and algorithmic issues. In particular, our model allows us to address in a unified way key issues such as Under what conditions will unlabeled data help and by how much? and How much data should I expect to need in order to perform well?. Another important part of this thesis is Active Learning for which we provide several new theoretical results. In particular, this dissertation includes the first active learning algorithm which works in the presence of arbitrary forms of noise, as well as a few margin based active learning algorithms. In the context of Kernel methods (another flourishing area of machine learning research), this thesis shows how Random Projection techniques can be used to convert a given kernel function into an explicit, distribution dependent set of features, which can then be fed into more general (not necessarily kernelizable) learning algorithms In addition, this work shows how such methods can be extended to more general pairwise similarity functions and also gives a formal theory that matches the standard intuition that a good kernel function is one that acts as a good measure of similarity. We thus strictly generalize and simplify the existing theory of kernel methods. Our approach brings a new perspective as well as a much simpler explanation for the effectiveness of kernel methods, which can help in the design of good kernel functions for new learning problems. We also show how we can use this perspective to help thinking about Clustering in a novel way. While the study of clustering is centered around an intuitively compelling goal (and it has been a major tool in manydifferent fields), reasoning about it in a generic and unified way has been difficult, in part due to the lack of a general theoretical framework along the lines we have for supervised classification. In our work we develop the first general discriminative clustering framework for analyzing accuracy without probabilistic assumptions. This dissertation also contributes with new connections between Machine Learning and Mechanism Design. Specifically, this thesis presents the first general framework in which machine learning methods can be used for reducing mechanism design problems to standard algorithmic questions for a wide range of revenue maximization problems in an unlimited supply setting. Our results substantially generalize the previous work based on random sampling mechanisms–both by broadening the applicability of such mechanisms and by simplifying the analysis. From a learning perspective, these settings present several unique challenges: the loss function is discontinuous and asymmetric, and the range of bidders' valuations may be large." @default.
• W36398315 created "2016-06-24" @default.
• W36398315 creator A5024803432 @default.
• W36398315 creator A5068544954 @default.
• W36398315 date "2008-01-01" @default.
• W36398315 modified "2023-09-26" @default.
• W36398315 title "New theoretical frameworks for machine learning" @default.
• W36398315 cites W112090490 @default.
• W36398315 cites W118545087 @default.
• W36398315 cites W14071851 @default.
• W36398315 cites W1479807131 @default.
• W36398315 cites W1480158300 @default.
• W36398315 cites W1489711815 @default.
• W36398315 cites W1495897132 @default.
• W36398315 cites W1502343786 @default.
• W36398315 cites W1507695921 @default.
• W36398315 cites W1510073064 @default.
• W36398315 cites W1516726196 @default.
• W36398315 cites W1520010392 @default.
• W36398315 cites W1520252399 @default.
• W36398315 cites W1526218779 @default.
• W36398315 cites W1528361845 @default.
• W36398315 cites W1531259569 @default.
• W36398315 cites W1535669030 @default.
• W36398315 cites W1542652324 @default.
• W36398315 cites W1542886316 @default.
• W36398315 cites W1548698874 @default.
• W36398315 cites W1549656520 @default.
• W36398315 cites W1553067018 @default.
• W36398315 cites W1554772789 @default.
• W36398315 cites W1558302528 @default.
• W36398315 cites W1560143607 @default.
• W36398315 cites W1560724230 @default.
• W36398315 cites W1564947197 @default.
• W36398315 cites W1569401919 @default.
• W36398315 cites W1572372689 @default.
• W36398315 cites W1574816920 @default.
• W36398315 cites W1579429723 @default.
• W36398315 cites W1585385982 @default.
• W36398315 cites W1585566614 @default.
• W36398315 cites W1587559562 @default.
• W36398315 cites W1595563493 @default.
• W36398315 cites W1604792744 @default.
• W36398315 cites W1607832978 @default.
• W36398315 cites W1648445109 @default.
• W36398315 cites W1653444175 @default.
• W36398315 cites W1658064490 @default.
• W36398315 cites W1676317136 @default.
• W36398315 cites W1744159168 @default.
• W36398315 cites W1781114614 @default.
• W36398315 cites W1781954958 @default.
• W36398315 cites W1822246767 @default.
• W36398315 cites W1899006432 @default.
• W36398315 cites W1938180907 @default.
• W36398315 cites W1956647075 @default.
• W36398315 cites W1964005287 @default.
• W36398315 cites W1966025295 @default.
• W36398315 cites W1969015668 @default.
• W36398315 cites W1970866964 @default.
• W36398315 cites W1971700966 @default.
• W36398315 cites W1973652906 @default.
• W36398315 cites W1973714307 @default.
• W36398315 cites W1974411071 @default.
• W36398315 cites W1976986203 @default.
• W36398315 cites W1979711143 @default.
• W36398315 cites W1980018091 @default.
• W36398315 cites W1980801609 @default.
• W36398315 cites W1987091651 @default.
• W36398315 cites W1990217074 @default.
• W36398315 cites W1995897489 @default.
• W36398315 cites W2001344406 @default.
• W36398315 cites W2005311763 @default.
• W36398315 cites W2010996873 @default.
• W36398315 cites W2011308746 @default.
• W36398315 cites W2014902932 @default.
• W36398315 cites W2015855658 @default.
• W36398315 cites W2017031328 @default.
• W36398315 cites W2017732166 @default.
• W36398315 cites W2019363670 @default.
• W36398315 cites W2029050771 @default.
• W36398315 cites W2029538739 @default.
• W36398315 cites W2031502124 @default.
• W36398315 cites W2034331023 @default.
• W36398315 cites W2037603696 @default.
• W36398315 cites W2037757210 @default.
• W36398315 cites W2040443294 @default.
• W36398315 cites W2043919728 @default.
• W36398315 cites W2045313701 @default.
• W36398315 cites W2047031390 @default.
• W36398315 cites W2047430378 @default.
• W36398315 cites W2048679005 @default.
• W36398315 cites W2055576996 @default.
• W36398315 cites W2056003475 @default.
• W36398315 cites W2056707879 @default.
• W36398315 cites W2057320839 @default.
• W36398315 cites W2061526129 @default.
• W36398315 cites W2062453462 @default.
• W36398315 cites W2064680241 @default.
• W36398315 cites W2065851930 @default.
• W36398315 cites W2069134712 @default.

• next