Paper
Saddle Point Evasion via Curvature-Regularized Gradient Dynamics
Authors
Liraz Mudrik, Isaac Kaminer, Sean Kragelund, Abram H. Clark
Abstract
Nonconvex optimization underlies many modern machine learning and control tasks, where saddle points pose the dominant obstacle to reliable convergence in high-dimensional settings. Escaping these saddle points deterministically and at a controllable rate remains an open challenge: gradient descent is blind to curvature, stochastic perturbation methods lack deterministic guarantees, and Newton-type approaches suffer from Hessian singularity. We present Curvature-Regularized Gradient Dynamics (CRGD), which augments the objective with a smooth penalty on the most negative Hessian eigenvalue, yielding an augmented cost that serves as an optimization Lyapunov function with user-selectable convergence rates to second-order stationary points. Numerical experiments on a nonconvex matrix factorization example confirm that CRGD escapes saddle points across all tested configurations, with escape time that decreases with the eigenvalue gap, in contrast to gradient descent, whose escape time grows inversely with the gap.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.15606v1</id>\n <title>Saddle Point Evasion via Curvature-Regularized Gradient Dynamics</title>\n <updated>2026-03-16T17:56:38Z</updated>\n <link href='https://arxiv.org/abs/2603.15606v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.15606v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Nonconvex optimization underlies many modern machine learning and control tasks, where saddle points pose the dominant obstacle to reliable convergence in high-dimensional settings. Escaping these saddle points deterministically and at a controllable rate remains an open challenge: gradient descent is blind to curvature, stochastic perturbation methods lack deterministic guarantees, and Newton-type approaches suffer from Hessian singularity. We present Curvature-Regularized Gradient Dynamics (CRGD), which augments the objective with a smooth penalty on the most negative Hessian eigenvalue, yielding an augmented cost that serves as an optimization Lyapunov function with user-selectable convergence rates to second-order stationary points. Numerical experiments on a nonconvex matrix factorization example confirm that CRGD escapes saddle points across all tested configurations, with escape time that decreases with the eigenvalue gap, in contrast to gradient descent, whose escape time grows inversely with the gap.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='math.OC'/>\n <category scheme='http://arxiv.org/schemas/atom' term='eess.SY'/>\n <published>2026-03-16T17:56:38Z</published>\n <arxiv:comment>This work has been submitted to the IEEE for possible publication. 6 pages, 3 figures</arxiv:comment>\n <arxiv:primary_category term='math.OC'/>\n <author>\n <name>Liraz Mudrik</name>\n </author>\n <author>\n <name>Isaac Kaminer</name>\n </author>\n <author>\n <name>Sean Kragelund</name>\n </author>\n <author>\n <name>Abram H. Clark</name>\n </author>\n </entry>"
}