Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more

Elad Tolochinsky, Ibrahim Jubran, Dan Feldman

نتاج البحث: نشر في مجلةمقالة من مؤنمرمراجعة النظراء

ملخص

Coreset (or core-set) is a small weighted subset Q of an input set P with respect to a given monotonic function f : R → R that provably approximates its fitting loss (Equation presented) to any given x ∈ Rd. Using Q we can obtain an approximation of x that minimizes this loss, by running existing optimization algorithms on Q. In this work we provide: (i) A lower bound which proves that there are sets with no coresets smaller than n = |P | for general monotonic loss functions. (ii) A proof that, with an additional common regularization term and under a natural assumption that holds e.g. for logistic regression and the sigmoid activation functions, a small coreset exists for any input P. (iii) A generic coreset construction algorithm that computes such a small coreset Q in O(nd + n log n) time, and (iv) Experimental results with open-source code which demonstrate that our coresets are effective and are much smaller in practice than predicted in theory.

اللغة الأصليةالإنجليزيّة
الصفحات (من إلى)21520-21547
عدد الصفحات28
دوريةProceedings of Machine Learning Research
مستوى الصوت162
حالة النشرنُشِر - 2022
الحدث39th International Conference on Machine Learning, ICML 2022 - Baltimore, الولايات المتّحدة
المدة: ١٧ يوليو ٢٠٢٢٢٣ يوليو ٢٠٢٢
https://proceedings.mlr.press/v162/

All Science Journal Classification (ASJC) codes

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

بصمة

أدرس بدقة موضوعات البحث “Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا