Sharpness-Aware Optimization for Stability Gap Reduction

Bachelor Thesis (2025)
Author(s)

K. Sycheva (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

G.M. van de Ven – Mentor (TU Delft - Pattern Recognition and Bioinformatics)

Tom Julian Viering – Mentor (TU Delft - Pattern Recognition and Bioinformatics)

A Hanjalic – Graduation committee member (TU Delft - Intelligent Systems)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
27-06-2025
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

One of the problems in continual learning, where models are trained sequentially on tasks, is a sudden drop in performance after switching to a new task, called stability gap. The presence of stability gap likely indicates that training is not done optimally. In this work we aim to address stability gap problem by using sharpness-aware optimization that biases convergence to flat minima. While flat minima are known to mitigate forgetting, their role in ensuring stable learning during task transitions remains unexplored. Through systematic analysis of two Entropy-SGD and C-Flat, we demonstrate that sharpness-aware optimizers produce smoother learning trajectories with reduced instability after task switch. Furthermore, we show that C-Flat’s second-order curvature approximation provides additional stabilization, suggesting that efficient Hessian-aware methods offer advantages for continual learning. The source code is available at Stability-Gap-SAM.

Files

Research_paper-13.pdf
(pdf | 1.93 Mb)
License info not available