Federated Learning (FL) can enable privacy-preserving distributed computation across several clients. It is used to federate knowledge from parties that do not wish to share their data. For example, project MELLODDY has applied it to drug discovery by federating models from several private laboratories to share the learning effort. But…

ML outcome optimization is the process of finding optimal feature values that give the model prediction minimum (or maximum) over a defined space. For black-box ML models, we cannot assume any of the usual smoothness properties for optimization, such as convexity or even differentiability. …

This is the story of a research project that didn’t quite make it. As every research project, it started with what seemed like a good and natural idea. As with most research projects, it didn’t end up as groundbreaking work. It wasn’t a catastrophic failure either. We believe that our…

This blog post highlights a minor discrepancy in the Hyperband method. It does not question the validity of the method nor its results. The spotted deviation leads Hyperband to underuse its allocated budget, so this may result in faster computation but degraded performance. Edit: We received an answer from the…

In our previous blog post, A Proactive Look at Active Learning Packages, we gave an overview of the most basic methods of active learning together with the most common Python packages as well as the more advanced methods they implement. For this second post, we’ll have a look at more…

If data acquisition is the very first step of any machine learning project, unfortunately, data doesn’t always come with the label of interest for the task at hand. It is often a very cumbersome task to (correctly!) label the data — and that’s where Active Learning comes in. Instead of…