ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2002.03176
8
1

On a scalable entropic breaching of the overfitting barrier in machine learning

8 February 2020
I. Horenko
ArXivPDFHTML
Abstract

Overfitting and treatment of "small data" are among the most challenging problems in the machine learning (ML), when a relatively small data statistics size TTT is not enough to provide a robust ML fit for a relatively large data feature dimension DDD. Deploying a massively-parallel ML analysis of generic classification problems for different DDD and TTT, existence of statistically-significant linear overfitting barriers for common ML methods is demonstrated. For example, these results reveal that for a robust classification of bioinformatics-motivated generic problems with the Long Short-Term Memory deep learning classifier (LSTM) one needs in a best case a statistics TTT that is at least 13.8 times larger then the feature dimension DDD. It is shown that this overfitting barrier can be breached at a 10−1210^{-12}10−12 fraction of the computational cost by means of the entropy-optimal Scalable Probabilistic Approximations algorithm (eSPA), performing a joint solution of the entropy-optimal Bayesian network inference and feature space segmentation problems. Application of eSPA to experimental single cell RNA sequencing data exhibits a 30-fold classification performance boost when compared to standard bioinformatics tools - and a 7-fold boost when compared to the deep learning LSTM classifier.

View on arXiv
Comments on this paper