Name
Efficiency
Date & Time
Thursday, October 26, 2023, 11:00 AM - 12:30 PM
Speakers
Arian Maleki, Columbia University Cross Validation In High-dimensional Settings We study the problem of out-of-sample risk estimation under the high dimensional settings where standard techniques such as K-fold cross-validation suffer from large biases. Motivated by the low bias of the leave-one-out cross validation, we study the theoretical properties of this estimate and its computationally-efficient approximation (called approximate leave-one-out) accurately, when the number of observations n, and the number of features p are both large while the ratio n/p remains bounded.
Cengiz Pehlevan, Harvard SEAS
Ankit Singh Rawat, Google Research, New York Knowledge Distillation: From Practice To Theory And Back Again
Anqi Mao, Google/New York University
Cengiz Pehlevan, Harvard SEAS
Ankit Singh Rawat, Google Research, New York Knowledge Distillation: From Practice To Theory And Back Again
Anqi Mao, Google/New York University
![Arian Maleki](http://assets.swoogo.com/uploads/thumb/3047756-65293bbb9d592.jpg)
![Cengiz Pehlevan](http://assets.swoogo.com/uploads/thumb/2998921-651c591737b6b.jpg)
![Ankit Singh Rawat](http://assets.swoogo.com/uploads/thumb/3023281-6520705f62faa.jpeg)
![Anqi Mao](http://assets.swoogo.com/uploads/thumb/3093738-65382016d679a.jpg)
Location Name
Kline Tower: 14th Floor
Full Address
219 Prospect St
New Haven, CT 06511
United States
New Haven, CT 06511
United States
Session Type
Workshop