Loss Functions, Complexities, and the Legendre Transformation

  • Authors:
  • Yuri Kalnishkan;Michael V. Vyugin;Volodya Vovk

  • Affiliations:
  • -;-;-

  • Venue:
  • ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper introduces a way of re-constructing a loss function from predictive complexity. We show that a loss function and expectations of the corresponding predictive complexity w.r.t. the Bernoulli distribution are related through the Legendre transformation. It is shown that if two loss functions specify the same complexity then they are equivalent in a strong sense.