Take a sneak peek at our latest work: “What if…? Pandemic Policy support to Guide a Cost-Benefit-Optimised, Country-Specific Response”
? Preprint HERE
After 18 months of responding to the COVID-19 pandemic, there is still no agreement on the optimal combination of mitigation strategies. This study proposes a data-driven approach to quantify the efficacy of the type, duration, and stringency of COVID-19 mitigation policies in terms of transmission control and economic loss, personalised to individual countries.
We will soon launch an accompanying interactive platform where you can pose questions like “What if…Senegal/Spain/etc. had a lockdown 2 weeks earlier…?“
Well done to our extraordinary students : Giorgio Mannarini, Francesco Posa, Thierry Bossy and Prakhar Gupta.
Introducing ? WAFFLE ? (Weighted Averaging For Federated LEarning)
? Preprint HERE
In #FederatedLearning, sometimes not every user’s data is useful to your task.
#WAFFLE uses the Euclidean distance between users’ updates to weigh their individual contributions and thus minimize the #personalized model loss on the specific user of interest.
Well done to the exceptional students behind this work:
?Martin B.eaussart and Felix Grimberg @MLO-iGH https://www.epfl.ch/labs/mlo/igh-intelligent-global-health
Prof Martin Jaggi wins the Credit Suisse teaching award
Supported by an army of recommendation letters from over 40 professors at EPFL, Prof Martin Jaggi wins the prestigious award for (among MANY other reasons) his innovative ML4Science initiative.
MLO’s first PhD graduation!
Dr Praneeth Karimireddy get’s a very well deserved prefix, after years of phenomenal productivity.
Lung ultrasound certification kicks off our clinical study in Cotonou
With our wonderful collaborators at CHUV, our LUSSTER research team in Benin will soon be collecting Lung UltraSound and Sound in TB-Endemic Regions.
Best paper award at ICML federated learning workshop
Well done to our MSc (now PhD) student, Felix Grimberg, for winning the best paper award at the ICML FL workshop.
See the submission HERE
Accepted paper at the ICML Interpretable ML in Healthcare workshop
Well done to our MSc student, David Roschewitz for his accepted paper on iFedAvg: interpertable interoperable federated learning. See submission HERE
Our incredible research site in South Africa is in the news
Read more about it HERE
We’re X-Prize winners
Our CODID-19 1YearHack team has been selected as winners for the XPrize on Collective Pandemic Intelligence for the “What If? Pandemic policy decision support” platform (presented at the AI for Good Global Summit)
We are hosting a yearlong hackathon for COVID and have a bunch of projects dedicated to better understanding and responding to the pandemic