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. 2105.08675
8
17

The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality

18 May 2021
Vincent Froese
Christoph Hertrich
R. Niedermeier
ArXivPDFHTML
Abstract

Understanding the computational complexity of training simple neural networks with rectified linear units (ReLUs) has recently been a subject of intensive research. Closing gaps and complementing results from the literature, we present several results on the parameterized complexity of training two-layer ReLU networks with respect to various loss functions. After a brief discussion of other parameters, we focus on analyzing the influence of the dimension ddd of the training data on the computational complexity. We provide running time lower bounds in terms of W[1]-hardness for parameter ddd and prove that known brute-force strategies are essentially optimal (assuming the Exponential Time Hypothesis). In comparison with previous work, our results hold for a broad(er) range of loss functions, including ℓp\ell^pℓp-loss for all p∈[0,∞]p\in[0,\infty]p∈[0,∞]. In particular, we extend a known polynomial-time algorithm for constant ddd and convex loss functions to a more general class of loss functions, matching our running time lower bounds also in these cases.

View on arXiv
Comments on this paper