Sample Compression for Real-Valued Learners

Aryeh Kontorovich, Menachem Sadigurschi

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations

Abstract

We give an algorithmically efficient version of the learner-to-compression scheme conversion in Moran and Yehudayoff (2016). We further extend this technique to real-valued hypotheses, to obtain a bounded-size sample compression scheme via an efficient reduction to a certain generic real-valued learning strategy. To our knowledge, this is the first general compressed regression result (regardless of efficiency or boundedness) guaranteeing uniform approximate reconstruction. Along the way, we develop a generic procedure for constructing weak real-valued learners out of abstract regressors; this result is also of independent interest. In particular, this result sheds new light on an open question of H. Simon (1997). We show applications to two regression problems: learning Lipschitz and bounded-variation functions.

Original languageEnglish
Pages (from-to)466-488
Number of pages23
JournalProceedings of Machine Learning Research
Volume98
StatePublished - 1 Jan 2019
Event30th International Conference on Algorithmic Learning Theory, ALT 2019 - Chicago, United States
Duration: 22 Mar 201924 Mar 2019

Keywords

  • Boosting
  • Compression Scheme
  • Empirical Risk Minimization
  • Regression

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Sample Compression for Real-Valued Learners'. Together they form a unique fingerprint.

Cite this