Today, machine learning and data science deal with tremendous amounts of high-dimensional data. Processing these data requires extensive computational resources (these often include large CPU and GPU clusters). It is expected that the amount of collected and analyzed data will grow significantly in the coming years. Thus, to advance and broaden the application of data analysis, it is crucial to design new, more efficient algorithms. The special quarter aims to develop new methods and techniques for working with high-dimensional data. We will investigate such topics as dimensionality reduction, sketching, low-distortion embeddings, and streaming. We will organize workshops to bring together researchers from theoretical computer science, machine learning, mathematics, and statistics.

• April 22-23: Workshop on Clustering
• May 4: IDEAL Seminar by Chandra Chekuri (UIUC)
• May 13: Workshop on Algorithms for Massive Data Sets
• May 27: Workshop on High-Dimensional Geometry and Analysis

Visit the events page to see a full listing of workshops coming up.