Monday, July 26 – Friday, July 30

Venue

This summer school will be a hybrid event. All talks will be streamed live online to registered participants. A limited in-person option will take place at the University of Wisconsin-Madison.

Sponsor

Summer School is sponsored by Institute for Foundations of Data Science (IFDS) at the University of Washington, the University of Wisconsin-Madison, the University of California-Santa Cruz, and the University of Chicago as well as the UW-Madison University Center of Excellence for Efficient and Robust Machine Learning, https://madlab.ml.wisc.edu. The IFDS is supported by the NSF TRIPODS Phase 2 program.

Description

This summer school will introduce participants to a broad range of cutting-edge areas in modern data science with an eye towards fostering cross-disciplinary research. Talks will cover both necessary foundational concepts from statistics, computer science and mathematics as well as latest developments. 

Pre-requisites

The intended audience for the summer school are advanced graduate students and postdoctoral researchers with a background in statistics, computer science, mathematics or related fields.

Registration

Prospective attendees are asked to submit an application form. Registration for the summer school is required but free. 

In-Person Option: An in-person option at the University of Wisconsin-Madison is available. Due to current physical distancing guidelines, attendance will be limited. Priority for in-person participation will be given to local UW-Madison applicants. The deadline to apply for the in-person option is JULY 2. Applicants will be notified by JULY 9. If we are unable to accommodate your in-person application, you will automatically be registered for the virtual option. In any case, links to the virtual stream will also be made available to the in-person participants.

Organizers

Sébastien Roch

Rob Nowak

Speakers and Topics

Cécile Ané
Cécile AnéStatistics & Botany, UW–Madison
Stochastic processes and algorithms for phylogenetics
Rina Foygel Barber
Rina Foygel BarberStatistics, U of Chicago
Lecture 1: Distribution-free inference: aims and algorithms
Lecture 2: Distribution-free inference: limits and open questions
Sebastien Bubeck
Sebastien BubeckMicrosoft Research
Lecture 1: Reminders on neural networks and high-dimensional probability
Lecture 2: A universal law of robustness via isoperimetry
Ilias Diakonikolas
Ilias DiakonikolasComputer Sciences, UW-Madison
Algorithmic Robust Statistics in High Dimensions
Kevin Jamieson
Kevin JamiesonComputer Science & Engineering, U Washington
Experimental Design for Linear Dynamical Systems
Dimitris Papailiopoulos,
Dimitris Papailiopoulos, Electrical & Computer Engineering, UW–Madison
A Summer Catalogue of Lottery Prizes: Finding Everything Within Random Nets
Jose Israel Rodriguez
Jose Israel RodriguezMathematics, UW–Madison
Sparse polynomial system solving and the method of moments
Karle Rohe
Karle RoheStatistics, UW–Madison
Interpretable embeddings with Varimax for graphs, text, and other things
+Lab session
Miaoyan Wang
Miaoyan WangStatistics, UW–Madison
Statistical foundations and algorithms for tensor learning

Schedule

(all times CDT)

Click speaker name for video

Monday, July 26th
Time Speaker
10:30-11:30 Karl Rohe
1:00-2:00 Karl Rohe
2:30-3:30 Jose Rodriguez
4:00-5:00 Jose Rodriguez
5:15-6:30 Poster Session
Tuesday, July 27th
Time Speaker
10:30-11:30 Cécile Ané
1:00-2:00 Cécile Ané
2:30-3:30 Miaoyan Wang
4:00-5:00 Miaoyan Wang
5:15-6:30 Poster Session
Wednesday, July 28th
Time Speaker
10:30-11:30 Dimitris Papailiopoulos
1:00-2:00 Dimitris Papailiopoulos
2:30-3:30 Sebastien Bubeck
4:00-5:00 Sebastien Bubeck
Thursday, July 29th
Time Speaker
10:30-11:30 Kevin Jamieson
1:00-2:00 Kevin Jamieson
2:30-3:30 Ilias Diakonikolas
4:00-5:00 Ilias Diakonikolas
Friday, July 30th
Time Speaker
10:30-11:30 Rina Foygel-Barber
1:00-2:00 Rina Foygel-Barber