Timezone: »

Understanding your Neighbors: Practical Perspectives From Modern Analysis
Sanjoy Dasgupta · Samory Kpotufe

Tue Jul 10 04:00 AM -- 06:15 AM (PDT) @ A9

Nearest-neighbor methods are among the most ubiquitous and oldest approaches in Machine Learning and other areas of data analysis. They are often used directly as predictive tools, or indirectly as integral parts of more sophisticated modern approaches (e.g. recent uses that exploit deep representations, uses in geometric graphs for clustering, integrations into time-series classification, or uses in ensemble methods for matrix completion). Furthermore, they have strong connections to other tools such as classification and regression trees, or even kernel machines, which are all (more sophisticated) forms of local prediction. Interestingly, our understanding of these methods is still evolving, with many recent results shedding new insights on performance under various settings describing a range of modern uses and application domains. Our aim is to cover such new perspectives on k-NN, and in particular, translate new theoretical insights (with practical implications) to a broader audience.

Website: http://www.princeton.edu/~samory/Documents/ICML-kNN-Tutorial.pdf

Author Information

Sanjoy Dasgupta (UCSD)

Sanjoy Dasgupta is a Professor in the Department of Computer Science and Engineering at UC San Diego. He works on algorithms for machine learning, with a focus on unsupervised and interactive learning.

Samory Kpotufe (Princeton University)

Samory Kpotufe is an Assistant Professor at ORFE, Princeton University, and works at the intersection of Machine Leaning and Nonparametric Statistics. In particular, his work on local predictive methods (k-NN, tree-based regression and classification) has won honors at leading Machine Learning venues (best student paper at COLT, and plenary presentations at NIPS, and AISTATS). Of relevance to this tutorial, Samory was an invited lecturer at the Machine Learning Summer School (MLSS), Cadiz 2016, where he covered topics on modern Nonparametrics.

More from the Same Authors