5 papers
Open Problem: Separating Geometric and Algorithmic Compression via Cayley-Table Completion
Dongsung Huh
Modern statistical learning theory and deep learning characterize generalization primarily in terms of continuous capacity control (e.g., norm-based regularization, margin maximiza…
Exact Symmetry as Algebra: Group-Structured Tensors that Enforce Physical Selection Rules
Paulina Hoyos, Shashanka Ubaru, Dongsung Huh +5
Symmetry determines which physical responses of molecules and crystals are allowed and underlies many models used throughout the physical sciences. Yet several widely used machine-…
A Differentiable Measure of Algebraic Complexity: Provably Exact Discovery of Group Structures
Dongsung Huh, Lior Horesh, Halyun Jeong
Discovering discrete algebraic rules from data is a fundamental challenge in machine learning. We formalize this problem through Cayley-table completion -- an algebraic counterpart…
Interpretable epistemic uncertainty decomposition in sequential generative models via polynomial chaos surrogates
Ramón Nartallo-Kaluarachchi, Shashanka Ubaru, Małgorzata J Zimoń +4
Sequential generative models conditioned on uncertain rewards are central to AI-driven scientific discovery, yet the epistemic uncertainty they inherit from imperfect reward estima…
Discovering Abstract Symbolic Relations by Learning Unitary Group Representations
Dongsung Huh
We investigate a principled approach for symbolic operation completion (SOC), a minimal task for studying symbolic reasoning. While conceptually similar to matrix completion, SOC p…