Laboratory for Information and Inference Systems – LIONS
We divide our research into two synergistic theory thrusts: information scalable optimization and data acquisition, and learning theory and methods for low-dimensional signal models. These research directions dovetail in order to develop a unified theory and practical toolset for adaptive representations, sampling and computational methods for high-dimensional data that feature structured geometric and combinatorial foundations.
Neurotechnology research at LIONS
Invasive brain recording is a promising technology for helping people who suffer from severe neurological disorders. Recorded brain signals can be used to control brain-machine interfaces with high precision, or to identify disease biomarkers with high sensitivity. Future wireless brain implants aim to process thousands of electrodes. However, processing and sending data from this many electrodes using a single chip has been an outstanding challenge due to the resource scarcity of implanted devices.
LIONS @ EUSIPCO 2020
LIONS were present at EUSIPCO 2020 with the tutorial entitled " Adaptive Optimization Methods for Machine Learning and Signal Processing". The 28th European Signal Processing Conference (EUSIPCO 2020) was to be held in August 2020 but due to Covid-19 it was postponed. The event took place virutally from 18-22 January 2021. Slides to the tutorial can be found on the following site.
LIONS @ DS3 summer school 2020
Professor Volkan Cevher was invited to give a talk, "Optimization challenges in adversarial ML", during Data Science Summer School, which offers courses and practical sessions covering the latest advances in data science. The 4th edition of Data Science Summer School was initially planned to be held in June 2020 but due to Covid-19 it was postponed. Eventually, the event was held virtually from 4-9 January 2021.