2022 Chicago Workshop on Coding and Learning

#machine #learning #coding #source #channel
Share
Source and channel coding have historically been the two fundamental tenets of information theory, respectively studying the ultimate performance limits to data compression and error correction. There have been many recent studies on the application of deep learning techniques to design or interpret new codes, and conversely, coding or information theoretic ideas have resulted in significant advances in various areas of machine learning. This workshop will bring together expert researchers who work in the intersection of coding and learning to present their latest contributions to the field, and also suggest future research directions. Specific topics of interest include, but not limited to:


- Interpretability/explainability in source and channel coding
- Deep learning aided coding schemes
- Coding for private and secure multi-agent learning
- Neural network compression, pruning, quantization
- Neural network capacity, approximation


  Date and Time

  Location

  Hosts

  Registration


  • Date: 02 Dec 2022
  • Time: 08:45 AM to 04:15 PM
  • All times are (UTC-06:00) Central Time (US & Canada)
  • Add_To_Calendar_icon Add Event to Calendar
If you are not a robot, please complete the ReCAPTCHA to display virtual attendance info.
  • Contact Event Host
  • Starts 25 November 2022 09:14 PM
  • Ends 02 December 2022 09:14 PM
  • All times are (UTC-06:00) Central Time (US & Canada)
  • No Admission Charge




Agenda

08:45-09:00: Erdem Koyuncu, University of Illinois Chicago. Opening remarks.
09:00-09:30: Salim El Rouayheb, Rutgers University. How to turn privacy on and off.
09:30-10:00: Emrah Akyol, SUNY Binghamton. Price of transparency in strategic classification.
10:00-10:30: Tudor Dumitras, University of Maryland, College Park. TBA
10:30-11:00: Osvaldo Simeone, King's College London. Reliable AI for communications via conformal prediction.
11:00-11:30: Daniela Tuninetti, University of Illinois Chicago. TBA
11:30-12:00: Deniz Gunduz, Imperial College London. TBA
12:00-12:30: Hulya Seferoglu, University of Illinois Chicago. TBA
12:30-12:30: Grab some lunch while the talks continue...
12:30-13:00: Joerg Kliewer, New Jersey Institute of Technology. How to teach an old dog some new tricks: Decoding of LDPC codes via reinforcement learning
13:00-13:30: Brad McDanel, Franklin & Marshall College. Dynamic neural networks: An overview and current trends
13:30-14:00: Aaron Wagner, Cornell University. TBA
14:00-14:30: Randall Berry, Northwestern University. TBA
14:30-15:00: Tsachy Weissman, Stanford University. On compression of, for, and with neural networks.
15:00-15:30: Natasha Devroye, University of Illinois Chicago. Towards interpreting deep-learned error-correcting codes.
15:30-16:00: Erdem Koyuncu, University of Illinois Chicago. TBA