[2405.19551] Tropical Gradient Descent

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

View PDF HTML (experimental) Abstract:We propose a gradient descent method for solving optimization problems arising in settings of tropical geometry - a variant of algebraic geometry that has attracted growing interest in applications such as computational biology, economics, and computer science. Our approach takes advantage of the polyhedral and combinatorial structures arising in tropical geometry to propose a versatile method for approximating local minima in tropical statistical optimization problems - a rapidly growing body of work in recent years. Theoretical results establish…

saved by

• Barton Rhodes

related reading

• [1605.08101] Global rates of convergence for nonconvex optimization on manifoldsarxiv.org
• [2605.15522] Stochastic Non-Smooth Convex Optimization with Unbounded Gradientsarxiv.org
• [2212.07677] Transformers learn in-context by gradient descentarxiv.org
• [2404.19756] KAN: Kolmogorov-Arnold Networksarxiv.org
• [2311.13159] Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flowarxiv.org
• [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
• Universal Complexity Bounds for Universal Gradient Methods in Nonlinear Optimizationarxiv.org
• DiffTaichi: Differentiable Programming for Physical Simulationarxiv.org
• [2503.22478] Almost Bayesian: The Fractal Dynamics of Stochastic Gradient Descentarxiv.org
• Hyper-Connectionsarxiv.org
• [2604.04891] Muon Dynamics as a Spectral Wasserstein Flowarxiv.org
• [2505.06589v1] Optimal Transport for Machine Learnersarxiv.org