distributional robustness 1generalization bounds 1optimal control 1transformer training 1Wasserstein distance 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness
KaÄan Akman, Naci Saldi, Serdar Yüksel
The paper derives finite‑sample generalization bounds for Transformer models by formulating their training as a finite‑horizon Markovian control problem, using quantized approximat…
cs.LG2026
An Optimal Control Approach To Transformer Training
KaÄan 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…