When Rates Are Geometric: Rate-Certificate Transfer for Contact Splittings in Optimization
Not on the map. Why?
Abstract (arXiv)
Discrete optimization algorithms are often analyzed through continuous-time limiting ODEs, but a convergence certificate for the ODE is not automatically one for the discrete algorithm. We develop contact Hamiltonian systems as a setting where the transfer can be made precise. A contact Hamiltonian H on J1(ℝn) obeys the intrinsic decay identity dot H = -H,partials H, so an augmented energy E built from H, together with the conformal rate partials H, is a continuous-time rate certificate whenever E controls the objective gap. Our main theorem states, under three named and independently checkable hypotheses, that an order-r contact splitting with step h transfers this certificate over the finite horizon set by backward error analysis. The discrete decay envelope is governed by the modified conformal factor up to O(hr) perturbations plus a backward-error shadowing defect, and the mechanism is inherited exactly because the modified Hamiltonian is itself a contact Hamiltonian. Quadratic heavy ball is a fully solvable example: its projected dissipative-leapfrog spectrum agrees with established conformal-symplectic optimization theory, while the augmented contact Hamiltonian yields a sharp objective-to-certificate comparison that verifies the transfer hypotheses. For strongly convex objectives with state-dependent damping, an explicit Bregman-type Lyapunov certificate instead transfers by an auxiliary-shadowing corollary. The decomposition H=K+V+D into kinetic, objective-encoding potential, and dissipation terms serves as a design template, with a catalogue of closed-form sub-flows including contact-specific damping families. Numerical experiments confirm the predicted conformal-factor tracking orders and show competitive performance on ill-conditioned benchmarks and deep-learning tasks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 43 references that are in the map. First posted on arXiv 26 Jul 2026.
Builds on
10 of 43 references.
References · 10
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Stochastic Gradient Hamiltonian Monte Carlocited by 343
- 2015A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insightscited by 206
- 2016A Variational Perspective on Accelerated Methods in Optimizationcited by 110
- 2018Understanding the Acceleration Phenomenon via High-Resolution Differential Equationscited by 69
- 2019A Dynamical Systems Perspective on Nesterov Accelerationcited by 33
- 2019Conformal Symplectic and Relativistic Optimizationcited by 29
- 2020On dissipative symplectic integration with applications to gradient-based optimizationcited by 23
- 2017Dissipativity Theory for Nesterov's Accelerated Methodcited by 22
- 2019Bregman dynamics, contact transformations and convex optimizationcited by 2
Built on by
Not cited yet.