2 papers
cs.LG2026
Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness
Kağan Akman, Naci Saldi, Serdar Yüksel
We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions. Building on the doubly lifted, measure-valued formulation of Transformer…
cs.LG2026
An Optimal Control Approach To Transformer Training
Kağan Akman, Naci Saldı, Serdar Yüksel
In this paper, we develop a rigorous optimal control-theoretic approach to Transformer training that respects key structural constraints such as (i) realized-input-independence dur…