← Back to all news
arXiv Machine Learning By Tong Wu, Andrew Campbell, Anna Scaglione

Graph Transfer Learning via Shared Latent Geometry: Theory and Applications

Read the original on arXiv Machine Learning →

arXiv:2606. 00716v1 Announce Type: new Abstract: Inference and control in engineered physical systems pay a heavy physics cost at deployment: state estimators, inverse-problem solvers, model-predictive controllers, schedulers, and observers are often not closed-form and must re-solve a numerical optimization per instance, with the operator re-supplied each time.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 26

Finite-Sample Metric Non-Collapse for Geometrically Supervised Latent World Models in Control

The paper presents a finite‑sample learning‑to‑control framework for geometrically supervised latent models of nonlinear deterministic systems. It introduces an encoder‑only local–global metric hinge that ensures directional resolution and state discrimination, and proves that any approximate empirical minimizer is pointwise co‑Lipschitz and uniformly approximately semiconjugate to the true dynamics under regularity assumptions. The results provide explicit bounds on approximation, sampling, and optimization errors, and demonstrate through controlled experiments that restoring metric resolution improves control performance.

By Alain Bensoussan, Minh-Nhat Phung, Minh-Binh Tran
More like this →
arXiv Machine Learning
Jun 2

World-Task Factorization for Robot Learning

arXiv:2606. 02027v1 Announce Type: cross Abstract: Robot learning must produce policies that generalize to new combinations of constraints, teammates, and environments.

By Eduardo Sebasti\'an, Adrian Pfisterer, Vito Mengers, Oliver Brock, Amanda Prorok
robotics
More like this →
arXiv Machine Learning
Sep 16

Certified Inference and Training for Deep Equilibrium Networks: A Continuation Framework with Polynomial Complexity Guarantees

The paper introduces a certified continuation framework for computing and training deep equilibrium networks (DEQs). It uses compact input homotopy and a rounded Newton tracker for inference, and augments local-plus-low-rank recurrence with programmable dormant bilinear rank‑one channels for training. The approach guarantees polynomial‑time bit complexity, with certified bounds on inference and training error budgets.

By Alex Borisevich
More like this →