[email]   [twitter]   [google scholar]   [github]   [cv]

Short bio. I’m a fourth-year PhD student in computer science at EPFL 🇨🇭 advised by Nicolas Flammarion. I did my MSc at Saarland University and the University of Tübingen, and interned at Adobe Research. My research is supported by the Google and OpenPhil PhD Fellowships.

Research interests. I’m interested in understanding why machine learning works and why it fails. I believe that understanding the training dynamics of gradient methods (especially, of SGD with large step sizes, procedures like sharpness-aware minimization, and fine-tuning language models) is key to understand generalization in deep learning. I also keep my interest in adversarial robustness (formal guarantees, square attack, fast adversarial training, RobustBench) and out-of-distribution generalization (curious ReLU properties, robustness on corruptions).

More details: https://www.andriushchenko.me/.