Zobrazeno 1 - 10
of 113
pro vyhledávání: '"Shai Ben-David"'
Autor:
Nicholas J. A. Harvey, Yaniv Plan, Hassan Ashtiani, Abbas Mehrabian, Christopher Liaw, Shai Ben-David
Publikováno v:
Journal of the ACM. 67:1-42
We prove that $\tilde{\Theta}(k d^2 / \varepsilon^2)$ samples are necessary and sufficient for learning a mixture of $k$ Gaussians in $\mathbb{R}^d$, up to error $\varepsilon$ in total variation distance. This improves both the known upper bounds and
Publikováno v:
STOC
A fundamental result in statistical learning theory is the equivalence of PAC learnability of a class with the finiteness of its Vapnik-Chervonenkis dimension. However, this clean result applies only to binary classification problems. In search for a
Publikováno v:
Nature Machine Intelligence. 1:44-48
The mathematical foundations of machine learning play a key role in the development of the field. They improve our understanding and provide tools for designing new learning paradigms. The advantages of mathematics, however, sometimes come with a cos
Autor:
Shai Ben- David, Giuseppe Curigliano, David Koff, Barbara Alicja Jereczek-Fossa, Davide La Torre, Gabriella Pravettoni
Artificial Intelligence for Medicine: An Applied Reference for Methods and Applications introduces readers to the methodology and AI/ML algorithms as well as cutting-edge applications to medicine, such as cancer, precision medicine, critical care, pe
Publikováno v:
Pattern Recognition. 120:108152
This paper makes a major step towards addressing a long-standing challenge in cluster analysis, known as the user’s dilemma, which is the problem of selecting an appropriate clustering algorithm for a specific task. A formal approach for addressing
Publikováno v:
ICDE
We view data de-duplication as a clustering problem. Recently, [1] introduced a framework called restricted correlation clustering (RCC) to model de-duplication problems. Given a set X, an unknown target clustering C* of X and a class F of clustering
Autor:
Shai Ben-David, Shai Shalev-Shwartz
Publikováno v:
Understanding Machine Learning. :372-379
Publikováno v:
Nature Machine Intelligence. 1:121-121
In the version of this Article originally published, the following text was missing from the Acknowledgements: ‘Part of the research was done while S.M. was at the Institute for Advanced Study in Princeton and was supported by NSF grant CCF-1412958
Autor:
Ruth Urner, Shai Ben-David
Publikováno v:
Annals of Mathematics and Artificial Intelligence. 70:185-202
The Domain Adaptation problem in machine learning occurs when the distribution generating the test data differs from the one that generates the training data. A common approach to this issue is to train a standard learner for the learning task with t
Publikováno v:
Proceedings of the VLDB Endowment. 2:598-609
One of the most prominent data quality problems is the existence of duplicate records. Current duplicate elimination procedures usually produce one clean instance (repair) of the input data, by carefully choosing the parameters of the duplicate detec