Jakob Robnik

Jakob Robnik

I am pushing the frontiers of data-driven science by developing and applying algorithms that scale to high-dimensional parameter spaces, large datasets or faint signals, while maintaining statistical rigor and scientific interpretability.

Publications

You can also find my articles on my Google Scholar profile.

Astronomy

[1] Jakob Robnik; Uroš Seljak. “Kepler data analysis: Non-Gaussian noise and Fourier Gaussian process analysis of star variability.” The Astronomical Journal 159(5), 224 (2020).

[2] Yan Liang; Jakob Robnik; Uroš Seljak. “Kepler-90: Giant transit-timing variations reveal a super-puff.” The Astronomical Journal 161(4), 202 (2021).

[3] Jakob Robnik; Uroš Seljak. “Matched filtering with non-Gaussian noise for planet transit detections.” Monthly Notices of the Royal Astronomical Society 504(4), 5829–5839 (2021).

[4] Jakob Robnik; Adrian E. Bayer; Maria Charisi; Zoltán Haiman; Allison Lin; Uroš Seljak. “Periodicity significance testing with null-signal templates: reassessment of PTF’s SMBH binary candidates.” Monthly Notices of the Royal Astronomical Society 534(2), 1609–1620 (2024).

[5] Jakob Robnik; Uroš Seljak. “Reassessment of Kepler’s habitable zone Earth-like exoplanets with data-driven null-signal templates.” Proceedings of the National Academy of Sciences (PNAS) 122 (41) (2025).

Computational Statistics

[1] Adrian E. Bayer; Uroš Seljak; Jakob Robnik. “Self-calibrating the look-elsewhere effect: fast evaluation of the statistical significance using peak heights.” Monthly Notices of the Royal Astronomical Society 508(1), 1346–1357 (2021).

[2] Jakob Robnik; Uroš Seljak. “Statistical significance testing for mixed priors: a combined Bayesian and frequentist analysis.” Entropy 24(10), 1328 (2022).

[3] Jakob Robnik; G. Bruno De Luca; Eva Silverstein; Uroš Seljak. “Microcanonical Hamiltonian Monte Carlo.” Journal of Machine Learning Research 24(311), 1–34 (2023).

[4] Jakob Robnik; Uroš Seljak. “Fluctuation without dissipation: Microcanonical Langevin Monte Carlo.” Proceedings of the 6th Symposium on Advances in Approximate Bayesian Inference, PMLR 253, 111–126 (2024).

[5] Emanuel Sommer; Jakob Robnik; Giorgi Nozadze; Uroš Seljak; David Rügamer. “Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks.” The Thirteenth International Conference on Learning Representations (2025).

[6] Jakob Robnik; Reuben Cohn-Gordon; Uroš Seljak. “Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo.” Advances in Neural Information Processing Systems (2025).

[7] Jakob Robnik; Reuben Cohn-Gordon; Uroš Seljak. “Black-box unadjusted Hamiltonian Monte Carlo.” arXiv preprint 2412.08876 (2025).

[8] Jakob Robnik; Uroš Seljak. “Faster parallel MCMC: Metropolis adjustment is best served warm” (2025).

High Energy Physics

In these papers I am the leading author; following field standards, authors are listed alphabetically.

[1] Robert Brandenberger; Lavinia Heisenberg; Jakob Robnik. “Non-singular black holes with a zero-shear S-brane.” Journal of High Energy Physics 2021(5), 090 (2021).

[2] Robert Brandenberger; Lavinia Heisenberg; Jakob Robnik. “Through a black hole into a new universe.” International Journal of Modern Physics D 30(14), 2142001 (2021).