Learning Convex Polyhedra with Margin

Lee Ad Gottlieb, Eran Kaufman, Aryeh Kontorovich, Gabriel Nivasch

Research output: Contribution to journalArticlepeer-review


We present an improved algorithm for quasi-properly learning convex polyhedra in the realizable PAC setting from data with a margin. Our learning algorithm constructs a consistent polyhedron as an intersection of about t t halfspaces with constant-size margins in time polynomial in t (where t is the number of halfspaces forming an optimal polyhedron). We also identify distinct generalizations of the notion of margin from hyperplanes to polyhedra and investigate how they relate geometrically; this result may have ramifications beyond the learning setting.

Original languageEnglish
Pages (from-to)1976-1984
Number of pages9
JournalIEEE Transactions on Information Theory
Issue number3
StatePublished - 1 Mar 2022


  • Classification
  • Dimensionality reduction
  • Margin
  • Polyhedra

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences


Dive into the research topics of 'Learning Convex Polyhedra with Margin'. Together they form a unique fingerprint.

Cite this