Statistical Aspects of Trustworthy Machine Learning



Nikola Konstantinov (ETH AI Center)

Nikola Konstantinov is a postdoctoral fellow at the ETH AI Center, working under the supervision of Prof. Martin Vechev and Prof. Fanny Yang. His research interests lie in the area of trustworthy machine learning, with a focus on robustness and fairness. Before ETH he was a PhD student at IST Austria, working in the group of Prof. Christoph Lampert. He was also part of the ELLIS PhD Program.



Short Abstract: Modern machine learning methods often require large amounts of labeled data for training. Therefore, it has become a standard practice to collect data from external sources, e.g. via crowdsourcing and by web crawling. Unfortunately, the quality of these sources is not always guaranteed and this may results in noise, biases and even systematic manipulations entering the training data. In this talk I will present some results on the statistical limits of learning in the presence of training data corruption. In particular, I will speak about the hardness of achieving fairness when a subset of the data is prone to adversarial manipulations. I will also discuss several results on the sample complexity of learning from multiple unreliable data sources.