Approximate computation and implicit regularization for very large-scale data analysis
Neyman Seminar
Jan 23, 2013, 04:00 PM - 05:00 PM | 1011 Evans Hall | Happening As Scheduled
Michael W. Mahoney, Stanford University
Statisticians and computer scientists adopt very different perspectives on
algorithms and data, and bridging this gap is essential to deliver on the
promise of developing statistically-principled methods for very large-scale
applications. A concept that lies at the heart of this disconnect is that
of regularization, a notion that has to do with how robust is the output of
an algorithm to the...