Center for Statistics and Machine Learning
The Center for Statistics and Machine Learning is a focal point for education and research in data science at Princeton University. By its nature, CSML is an interdisciplinary enterprise. The center’s mission is to foster and support:
- a community of scholars addressing the manifold challenges of modern data-driven exploratory research
- the development of innovative methodologies for extracting information from data
- the education of students in the foundations of modern data science
The center supports and collaborates on research and teaching that combines insights from computation, machine learning, and statistics with specific application domains. To encourage a flow of ideas, CSML welcomes connections with faculty, departments, centers and institutes across the Princeton campus. In addition to exploring novel applications, the center supports innovations in the theoretic foundations of data science, including advanced algorithms for big-data problems, machine learning, optimization, and statistics.
Established in July 2014, the Center for Statistics and Machine Learning is part of a rich and influential history in data science at Princeton University. Individuals such as Samuel Wilks, John Tukey, William Feller, Alonzo Church, Alan Turing, and John Von Neumann played key roles in pioneering the use of statistics, probabilistic models, and computers to solve real world problems. The Cooley–Tukey FFT algorithm (1965), and the initiation of the ImageNet database (2009) are two prominent examples of Princeton’s prior contributions to data science.
The center is housed at 26 Prospect Avenue (Bendheim Center for Finance Building, and formerly Dial Lodge).
Convergence Rates of Stochastic Algorithms in Nonsmooth Nonconvex OptimizationThu, Nov 14, 2019, 4:30 pmLocation: B205 Engineering QuadrangleSpeaker(s):
Machine Learning for the Sciences
Can learning theory resist deep learning?
Diving into TensorFlow 2.0