2020 Information Theory and ApplicationsWorkshop

Sunday–Friday, February 2–7

Catamaran Resort, Pacific Beach, San Diego

A casual gathering of researchers applying theory to diverse areas in science and engineering

Presenting at ITA

ITA presentations are by invitation only. If you have not been to ITA, or you are listed as not-presenting and would like to give a talk, please email us a short description of your proposed presentation. If you are a student and would like to present a poster, please also include your advisor’s name and email. If you are a graduating student or a postdoc and would like to participate in Graduation Day, please ask your advisor to nominate you.

This year’s workshop will also feature special invited sessions, consisting of 3–4 speakers. If you would like to organize such a session, please email us the proposed topic and potential speakers.

Please send all emails to ita@ucsd.edu.

Plenary Sessions

Monday

Deep Learning for Source and Channel Coding

University of Wisconsin
Tuesday

Reinforcement Learning

Princeton University
University of Washington
Wednesday

Algorithmic Game Theory

Thursday

Constrained Learning

Stanford University
Princeton University
Friday

Deep Learning

University of Toronto
University of Toronto

Invited Sessions

Scroll or Swipe to view all

Timely Transmissions
Richard Wesel

Ahmed Arafa

Mai Vu

Ori Shantal

Deep Generative Models
Soheil Feizi

Alex Dimakis

Sewoong Oh

Paul Hand

Robotics and Control I
Nikolay Atanasov

Houssam Abbas

Ali Agha

Nikolay Atanasov

Information Theory to Practical Learning
Gil Shamir

Alex Alemi

Gil Shamir

Rohan Anil

Julian Grady

Robotics and Control II
Yasser Shoukry

Hamid Jafarkhani

Yasser Shoukry

Ankur Mehta

Tensor Methods
Anna Ma

Jamie Haddock

Vagelis Papalexakis

Longxiu Huang

Alona Kryshchenko

Control and Game Theory
Behrouz Touri

Jorge Poveda

Xudong Chen

Jason Marden

Ben Recht

Physics and Machine Learning
Lenka Zdeborova

Surya Ganguli

Lenka Zdeborova

Giulio Biroli

Marylou Gabrie,

People, AI, and Fairness
Nihar Shah

Ashia Wilson

Lillian Ratliff

Nihar Shah

DNA Storage
Ryan Gabrys

Farzad Farnoud

Mahdi Cheraghchi

Ilan Shomorony

Zhiying Wang

Robotics and Control III
Konstantinos Karydis

Vikas Dhiman

Konstantinos Karydis

Optimal Transport
Ayfer Ozgur

Ziv Goldfeld

Xianfeng Gu

Xiugang Wu

Theory of Deep Learning
Marco Mondelli

Marco Mondelli

Matus Telgarsky

Quanquan Gu

Nathan Srebro

Differentially Private Statistics
Gautam Kamath

Rachel Cummings

Gautam Kamath

Clement Canonne

Ameya Velingker

Low-Rank Approximation
David Woodruff

David Woodruff

Cameron Musco

Samson Zhou

Aditya Bhaskara

High Dimensional Statistics
Gautam Dasarathy

Pradeep Ravikumar

Anshumali Shrivastava

Gautam Dasarathy

Giulia Pedrielli

Graph Signal Processing I
Santiago Segarra

Basak Guler

Antonio Marques

Solmaz Kia

Graph Signal Processing II
Florian Meyer

Yanning Shen

Santiago Segarra

Farshad Lahouti

Geert Leus

Federated Learning: Compression & Privacy
Peter Kairouz

Badih Ghazi

Abhradeep Thakurta

Ayfer Ozgur

Distributed Learning,Estimation,and Testing
Hamed Hassani

Jayadev Acharya

Gauri Joshi

Hamed Hassani

Salman Avestimehr

Coded computing and learning
Salman Avestimehr

Rashmi Vinayak

Viveck Cadambe

Saeid Sahraei

Privacy-preserving ML
Vitaly Feldman

Adam Smith

Audra McMillan

Vitaly Feldman

Shahab Asoodeh

Bioinformatics
Siavash Mirarab

Adam MacLean

Siavash Mirarab

Sriram Sankararaman

Yana Safonova

Topics in machine learning theory
Siva Theja

Guannan Qu

Abhishek Gupta

Christina Lee Yu

R. Srikant

Federated Learning: Theory and Practice
Ananda Suresh

Mehryar Mohri

Peter Kairouz

Ananda Theertha Suresh

Optimization algorithms for federated learning
Arya Mazumdar

Arya Mazumdar

Himanshu Tyagi

Satyen Kale

Aryan Mokhtari

Block chains:
Sreeram Kannan

Swanand Kadhe

David Tse

Aniket Kate

Dahlia Malhki

Privacy and Fairness in ML
Flavio Calmon

Swati Gupta

Nadia Fawaz

Flavio Calmon

Steven Wu

Robust Learning
Lalitha Sankar

Jiantao Jiao

Ludwig Schmidt

Lalitha Sankar

Cyrus Rashtchian

Statistics and Mathematics
Peter Grunwald

Peter Grunwald

Aaditya Ramdas

Urbashi Mitra

Amit Sahai

Optimization and Deep Learning
Meisam Razaviyayn

Ioannis Mitliagkas

Chi Jin

Mahdi Soltanolkotabi

Meisam Razaviyayn

Coding for Networks
Hessam Mahdavifar

Jung Hyun Bae

Krishna Narayanan

Lele Wang

Soheil Mohajer

Schedule Outline

Sunday, February 2nd, 2020
3:30 PMKick off the workshop with Super Bowl LIV live at the Plumeria Suite, food and drinks.
6:30 PMOpening Ceremony: reception with heavy hors d'oeuvres and south-of-the-border entertainment!
Default Schedule
8:15 AMBreakfast (included with registration)
9:00 AMSessions Begin
Monday, February 3rd, 2020
9:00 AM
9:50 AMBreak
10:00 AMSessions: Timely Transmissions, Deep Generative Models, Machine Learning Applications I, Coding Theory I, Deep Learning I
11:00 AMBreak
11:20 AMSessions: Shannon Theory, Deep Learning II, Wireless I, Robotics and Control I, Data Fitting
12:20 AMLunch
1:30 PMPlenary Session: Deep Learning for Source and Channel Coding — Alex Dimakis, Rebecca Willet, Pramod Viswanath
2:40 PMBreak
2:50 PMSessions: Coding Theory II, Information Theory to Practical Learning, General Machine Learning, Robotics and Control II, Tensor Methods
4:30 PMSessions: Coding Theory III, Communication Channels I, Wireless III, Optimization I, Coding and Caching
EveningPredict, watch, and debate the Iowa Caucuses results, the opening salvo of a crazy election year.
Tuesday, February 4th, 2020
9:00 AMSessions: Coding and Computing I, Learning Theory I, Physics and Machine Learning, Coding Theory IV, Wireless IV, Communication Channels II
10:20 AMBreak
10:40 AMSessions: Control and Game Theory, Information Theory and Statistics, People, AI, and Fairness, DNA Storage, Wireless V, Source and Channel Coding
12:00 PMLunch
1:40 PMPlenary Session: Reinforcement Learning — Ben Recht, Elad Hazan, Sham Kakade
2:50 PMBreak
3:10 PMSessions: Reinforcement Learning I, Graphs and Matrices, Robotics and Control III, Statistics I, Deep Learning in Communications, Deep Learning III
4:10 PMBreak
4:30 PMSessions: Control Theory I, Sparsity, Coding Theory V, Wireless VI, Information Theory of Learning I, Reinforcement Learning II
EveningState of the Union Address, Cheer and Jeer the POTUS State of the Union Address.
Wednesday, February 5th, 2020
9:00 AMSessions: Trustworthy Machine Learning, Deep Learning IV, Security, Optimal Transport, Wireless Communication
10:00 AMBreak
10:20 AMGraduation Day talks, part 1
11:00 AMBreak
11:20 AMGraduation Day talks, part 2
12:00 PMGraduation Day posters and catered lunch
2:20 PMPlenary Session: Algorithmic Game Theory — Vijay Vazirani, Ruta Mehta, Joel Sobel
3:30 PMGroup photo
4:00 PMContraventional : A broader view of Machine Learning
and
An Update from NSF
5:00 PMBreak
6:15 PMBanquet reception at the Aviary (ticket required)
7:00 PMQuinceañera Banquet with surpises and prizes(ticket required)
Thursday, February 6th, 2020
9:00 AMSessions: Theory of Deep Learning, Learning Theory II, Online Learning I, Differentially Private Statistics, Low-Rank Approximation, Wireless VII
10:20 AMBreak
10:40 AMSessions: Learning in Graphs, Deep Learning V, High Dimensional Statistics, Coding and Computing II, Overparametrization, Optimization II
12:00 PMLunch (on your own); soccer, volleyball, and other games by the beach
1:40 PMPlenary Session: Constrained Learning — Gregory Valiant, Ran Raz, Kunal Talwar
2:50 PMBreak
3:10 PMSessions: Federated Learning: Compression & Privacy, Control Theory II, Learning in Networks, Age of Information, Graph Signal Processing I, Coded Computing and Learning
4:10 PMBreak
4:30 PMSessions: Coding and Information retrieval, Bioinformatics, Distributed Learning, Estimation, and Testing, Privacy-preserving ML, Graph Signal Processing II, Robust Learning I
5:50 PMBreak
7:00 PMBonfire by the ocean
Friday, February 7th, 2020
9:00 AMSessions: Topics in machine learning theory, Privacy and Fairness in ML, Federated Learning: Theory and Practice, Block Chain, Algorithm for Matrices and Network, Statistics and Mathematics
10:20 AMBreak
10:40 AMSessions: Reinforcement Learning III, Quantum Theory, Online Learning II, Optimization III, Robust Learning II, Deep Learning VI
12:00 PMStudent Posters and Lunch
1:40 PMPlenary Session: Deep Learning — Kamalika Chaudhuri, Ruslan Salakhutdinov, Daniel Roy
2:50 PMBreak
3:05 PMSessions: Statistics III, Theory meets Practice, Optimization for Federated Learning, Optimization and Deep Learning, Games and Adversaries, Coding for Networks
4:25 PMBreak
4:35 PMClosing Ceremony and Farewell Bash
Saturday, February 8th, 2020
8:30 - 4:00Learn to Do: Deep- and Reinforcement-learning tutorials and expository machine-learning talks.

Daily Schedule

Every day, two sessions will be held on the Bahia Belle shown in the background

Location Location Location

Catamaran Resort, Pacific Beach, San Diego

The Catamaran kindly gave us similar rates as last year: Garden view: $146, Studio: $159, Ocean/bay view suite: $174. Parking: $26/day. In past years we ran out of rooms, so please book soon.

Special Events

ICML
ICML Paper-ation
Prepare your ICML paper at ITA
Information Theory Society
Information Theory Society
President's address and town hall.
Lunch and Plenary Ice breaker
Lunch and Plenary Ice breaker
Get to know workshop attendees
Graduation Day
Graduation Day
Research Overview Presentations
An Update from NSF
An Update from NSF
Everything you always wanted to know about NSF...
Student Posters
Student Posters
Show off your research!

Social Events

Super Bowl Party
Super Bowl LIV
Kick off the workshop
Iowa Caucuses
Iowa Caucuses
Let chaos begin
State of the Union Address
State of the Union Address
POTUS SOTU 2020
Flower Workshop
Flower Workshop
Design your own Banquet Bouquet
Bonfire
Bonfire
Bonfire by the beach
Final Bash
Final Bash
Fun, food and farewell!

Learn To Do

Tutorials and expository talks on Machine Learning

Saturday 2/8, 8:30 - 4:00, at the Catamaran. Registration required.

Deep learning
Deep Learning
Reinforcement learning
Reinforcement Learning
Robert Kleinberg, Cornell, and Alex Slivkins, Microsoft
Safety and Luckiness
Safety and Luckiness
Machine Learning
Machine Learning

EATA

Daybreak

Daily
8:15 AM

Nightcap

Daily
6:30 PM

Reception

Sun
6:30 PM

IT-Session Lunch

(for Attendees Only)

Mon
12:30-2 PM

Graduation
Lunch

Wed
12 PM

Banquet

Wed
6:30 PM

Poster Lunch

Fri
12:30 PM

Farewell

Fri
4:30 PM

Sponsors

GoogleQualcommQualcomm InstituteUCSD HDSI

Code of Conduct

The ITA workshop and community are built upon the core values of collegiality, support, and dignity for all, and we endorse the conference codes of conduct adopted by the ACM, IEEE, and the Information Theory Society. Disrespectful, offensive, and inappropriate behavior is not welcome at our events. If you observe such behavior, please inform one of our staff or email us at ita@ucsd.edu.