Wasserstein Saddle-Free Newton: Saddle Escape and Local Spectral Convergence

Abstract

Extending saddle-free Newton methods to Wasserstein space requires controlling Hessian dependent operators along nonlinear transport trajectories and accounting for a Hessian spectrum that may accumulate at zero. We address these challenges through Wasserstein Saddle-Free Newton (WSFN), a second-order method for nonconvex optimization over Wasserstein space that preconditions the Wasserstein gradient by a regularized inverse square root Hessian operator. The dynamics exploit curvature magnitude while maintaining negative curvature repulsion and positive curvature attraction, avoiding key Wasserstein Newton limitations. Whereas previous Wasserstein saddle escape results rely on perturbed first-order dynamics, WSFN uses curvature both to modify the deterministic transport and to construct the perturbation mechanism. Our analysis combines stability estimates for Hessian operators with a perturbative saddle escape argument to establish polynomial time convergence to approximate second-order stationarity under regularity of landscape assumptions. The contribution of the saddle curvature parameter δ improves from Õ(δ⁻⁴) for prior perturbed first-order Wasserstein methods to Õ(δ⁻³). For benign landscapes, this implies proximity to global minimizers. The cubic dependence corresponds to the scale of the objective decrease that can be guaranteed from negative curvature under Lipschitz Hessian regularity. Near a minimizer, the possible absence of a uniform spectral gap prevents a uniform contraction result and instead calls for a spectral characterization. We prove geometric contraction of the linearized dynamics on positive curvature spectral bands bounded away from zero and polynomial decay under spectral source conditions. Together, these results connect quantitative saddle escape with the local spectral behavior of second-order Wasserstein dynamics.

Hybrid Newton-BFGS high-index saddle dynamics for accelerating saddle-point searches
Jianyuan Yin, Lei Zhang, Shixue Zhang
arXiv5 Nov 2026PreprintarXiv licenceFull textNumerical analysis & scientific computingarXiv
Finite Spectral Depth Controls Gaussian Entrance Rank and Avoidance of the First Gradient-Flow Saddle
Yanlin Long
arXiv3 Nov 2026PreprintCC BY 4.0Full textOptimisation & controlarXiv
Riemannian ascent--descent for nonconvex nonconcave minimax landscapes: convergence to basin saddle points and applications to distributionally robust optimization
Rishabh Dixit, Pranav Upadrashta, Alex Cloninger
arXiv12 Sep 2026PreprintarXiv licenceFull textOptimisation & control StatisticsarXiv
Equidistribution of saddle periodic points for automorphisms on compact Kähler manifolds
Muhan Luo, Qi Zhou
arXiv29 Sep 2026PreprintarXiv licenceFull textAnalysis & PDEs Dynamical systemsarXiv
Classification of Double Saddle-Point Systems
Susanne Bradley, Chen Greif
arXiv22 Oct 2026PreprintCC BY 4.0Full textNumerical analysis & scientific computingarXiv

Cite

BibTeX RIS

BibTeX

@misc{lascu2026wasserstein,
  title = {{Wasserstein Saddle-Free Newton: Saddle Escape and Local Spectral Convergence}},
  author = {Razvan-Andrei Lascu and Taiji Suzuki},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2605.17963},
  eprint = {2605.17963},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.17963},
}

RIS

TY  - UNPB
TI  - Wasserstein Saddle-Free Newton: Saddle Escape and Local Spectral Convergence
AU  - Razvan-Andrei Lascu
AU  - Taiji Suzuki
PY  - 2026
DA  - 2026/09/26
PB  - arXiv
DO  - 10.48550/arxiv.2605.17963
UR  - https://arxiv.org/abs/2605.17963
AB  - Extending saddle-free Newton methods to Wasserstein space requires controlling Hessian dependent operators along nonlinear transport trajectories and accounting for a Hessian spectrum that may accumulate at zero. We address these challenges through Wasserstein Saddle-Free Newton (WSFN), a second-order method for nonconvex optimization over Wasserstein space that preconditions the Wasserstein gradient by a regularized inverse square root Hessian operator. The dynamics exploit curvature magnitude while maintaining negative curvature repulsion and positive curvature attraction, avoiding key Wasserstein Newton limitations. Whereas previous Wasserstein saddle escape results rely on perturbed first-order dynamics, WSFN uses curvature both to modify the deterministic transport and to construct the perturbation mechanism. Our analysis combines stability estimates for Hessian operators with a perturbative saddle escape argument to establish polynomial time convergence to approximate second-order stationarity under regularity of landscape assumptions. The contribution of the saddle curvature parameter δ improves from Õ(δ^−4) for prior perturbed first-order Wasserstein methods to Õ(δ^−3). For benign landscapes, this implies proximity to global minimizers. The cubic dependence corresponds to the scale of the objective decrease that can be guaranteed from negative curvature under Lipschitz Hessian regularity. Near a minimizer, the possible absence of a uniform spectral gap prevents a uniform contraction result and instead calls for a spectral characterization. We prove geometric contraction of the linearized dynamics on positive curvature spectral bands bounded away from zero and polynomial decay under spectral source conditions. Together, these results connect quantitative saddle escape with the local spectral behavior of second-order Wasserstein dynamics.
ER  -

Abstract

Related

Cite