Author

B. Hamzi

3 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.

Open access Oct 2026

Bridging Machine Learning and Algorithmic Information Theory, Part VII: Algorithmic Information Kernels and Kernel Discrepancies on Countable Spaces

Compression-based dissimilarities such as the normalized compression distance are widely used, but direct exponentiation need not produce a positive semidefinite kernel. We develop a systematic interface between prefix algorithmic information theory and three kernel discrepancy methods on finite or countable spaces: ma...

B. Hamzi, Marcus Hutter, H. Owhadi · Entropy · 0 citations

Open access Sep 2026

Category-Native Solomonoff Approximation: From Algorithmic Geometry to Kernels, Operators, and Induction

This theory-and-position paper argues that practical approximation must be category-native: one should first declare the mathematical category in which a computable shadow will live, then use that category’s native comparison functional, complexity code, and inductive object.

B. Hamzi, Marcus Hutter · Entropy · 1 citation

#machine learning Sep 2025

Data-efficient Kernel Methods for Learning Hamiltonian Systems

This work proposes kernel-based methods for identifying and forecasting Hamiltonian systems directly from trajectory data, and provides a more general, problem-agnostic numerical framework that goes beyond Hamiltonian systems and can be used for data-driven learning of arbitrary dynamical systems.

Yasamin Jalalian, Mostafa Samir, B. Hamzi et al. · arXiv.org · 4 citations