Efficient Kirszbraun Extension with Applications to Regression

Hanan Zaichyk, Armin Biess, Aryeh Kontorovich, Yury Makarychev

Research output: Working paper/PreprintPreprint

40 Downloads (Pure)

Abstract

We introduce a framework for performing regression between two Hilbert spaces. This is done based on Kirszbraun's extension theorem, to the best of our knowledge, the first application of this technique to supervised learning. We analyze the statistical and computational aspects of this method. We decompose this task into two stages: training (which corresponds operationally to smoothing/regularization) and prediction (which is achieved via Kirszbraun extension). Both are solved algorithmically via a novel multiplicative weight updates (MWU) scheme, which, for our problem formulation, achieves a quadratic runtime improvement over the state of the art. Our empirical results indicate a dramatic improvement over standard off-the-shelf solvers in our setting.
Original languageEnglish
StatePublished - 1 May 2019

Keywords

  • Computer Science - Machine Learning
  • Statistics - Machine Learning

Fingerprint

Dive into the research topics of 'Efficient Kirszbraun Extension with Applications to Regression'. Together they form a unique fingerprint.

Cite this