Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance

NeurIPSSpotlight2025

Authors
Qiujiang Jin, Aryan Mokhtari
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

In this paper, we establish global non-asymptotic convergence guarantees for the BFGS quasi-Newton method without requiring strong convexity or the Lipschitz continuity of the gradient or Hessian…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

convergence

← All NeurIPS 2025 Spotlight papers · Browse the whole archive