I’m back from my first ever school that I attended as a lecturer! It was Nordita Winter School on ML <-> physics. You can check out my lectures and tutorials on neural network loss landscapes and interpretability here 🙂

It is time to grow a group! If you are curious about interpretable machine learning for quantum problems, consider applying for a PhD student or a postdoctoral position! 🙂

Level up! Starting this October, I’m kicking off a research group within aQa at Leiden University in Netherlands as an assistant professor! Just signed my soul away, I mean, a contract. I’m mostly excited and a bit frantic. Also, I try to forget that society has some expectations towards professors, but my friends tease me terribly about it 😛

I just got back from an extremely interesting Lindau Nobel Laureate Meeting. Here are some thoughts of mine.

Our work on the Goldilocks zone of neural network initialization, led by fantastic newly defended Dr. Artem Vysogorets, has been accepted to ICML ’24!  We derived conditions for the excess of positive eigenvalues of the loss Hessian at the initialization, which was observed by Fort & Scherlis (2019) to correlate very well with the network trainability (and even better generalization). We also play with networks initialized outside the Goldilocks zone and describe the failure modes. It’s my first ICML paper, I’m a bit too happy 😛

Exciting new work on arXiv! With awesome experimental collaborators, we developed a graph algorithm to identify laser cooling schemes straight from spectroscopic data! Spoiler alert: it’s really fast, and results are super promising!

We have a contract with Cambridge University Press to publish our book “Machine learning in quantum sciences”! We expect printed copies in July 2024 😉

I won a distinction in the Polish Physical Society contest for the best PhD thesis in physics defended in Poland in 2022 🙂

A new adventure as a Flatiron Research Fellow unveils!

I defended with honours my PhD thesis titled “Quantum many-body physics with ultracold atoms and molecules: exact dynamics and machine learning”. It was a crazy ride, and I loved every minute of it (weeell, a large majority!).

I am extremely happy and honoured to announce that I was awarded the START fellowship of the Foundation for Polish Science for the best scientists under 30!

The first version of our Book “Modern applications of machine learning in quantum sciences” is ready! It was a challenging and very fruitful 8 months of work of both participants and lecturers of our Summer School: Machine Learning in Quantum Physics and Chemistry in Warsaw 🙂

“Towards interpretable and reliable machines learning physics” – My first invited talk ever, and it’s on the APS March Meeting in beautiful Chicago (I just love skyscrapers)! The recording is available here.

It was a month of amazing discussions and breathtaking views! I visited and gave seminars in the groups of Alán Aspuru-Guzik (Univ. of Toronto), Roman Krems (Univ. of British Columbia, Vancouver), Eun-Ah Kim (Cornell University, Ithaca), Tanya Zelevinsky (Columbia University, NY), Ana Maria Rey (JILA, Boulder), and Kang-Kuen Ni (Harvard University, Boston).