Author

P. Zaika

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Nov 2025

When is a System Discoverable from Data? Discovery Requires Chaos

The deep learning revolution has enabled major AI advances in physical sciences, particularly in discovering dynamical systems from observational data. Yet the reliability of learned surrogates and symbolically discovered models is often undermined by non-uniqueness: models may fit observed trajectories perfectly, but...

Zakhar Shumaylov, P. Zaika, Philipp Scholl et al. · arXiv.org · 11 citations · ⚡1

#machine learning Preprint Oct 2026

Non-Euclidean Gradient Descent Has Many Edges of Stability

Recent observations that deep learning models train at the edge of stability have renewed interest in understanding stability properties of classical optimization algorithms. For quadratic objectives, standard gradient descent has a sharp stability threshold: it converges from every initialization when $\eta<2/L$, dive...

P. Zaika, Zakhar Shumaylov · 0 citations