PulseAugur
EN
LIVE 13:16:04

Paper analyzes fitting logic-based hypotheses over infinite structures

This paper explores the computational and descriptive complexity of fitting problems, specifically when dealing with logic-based hypothesis classes over infinite structures. It investigates how to determine if a given finite sample of inputs and outputs can be explained by a function within a particular class. The research focuses on decidable structures like the real ordered field and Presburger arithmetic, as well as broader classes defined by combinatorial or model-theoretic properties, examining the role of queries in this fitting process. AI

RANK_REASON The cluster contains a single academic paper discussing theoretical computer science concepts. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Michael Benedikt, Alessio Mansutti ·

    How (and when) can you fit examples to logic-based hypothesis classes over infinite structures?

    arXiv:2606.01107v1 Announce Type: cross Abstract: We study fitting problems, sometimes called ``training problems'', where we have a finite sample consisting of inputs and outputs, and we want to know whether there is a function in a certain class that could produce these outputs…