arXiv Machine Learning

Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness

arXiv:2607. 27975v1 Announce Type: new Abstract: We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions.

Hugging Face Trending Papers
Jul 30

Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness

We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions. Building on the doubly lifted, measure-valued formulation of Transformer dynamics, we view data sets as probability laws on pairs of empirical input-output measures, allowing us to interpret the training problem as a finite-horizon Markovian control problem.

arXiv Machine Learning
Jun 18

Generative models for decision-making under distributional shift

arXiv:2604. 04342v2 Announce Type: replace Abstract: Many data-driven decision problems are formulated using a nominal distribution estimated from historical data, while performance is ultimately determined by a deployment distribution that may be shifted, context-dependent, partially observed, or stress-induced.

By Xiuyuan Cheng, Yunqin Zhu, Yao Xie
arXiv Machine Learning
Jun 29

PAC-Bayesian Certificates for Quadratic Closed-Loop Control

arXiv:2606. 28281v1 Announce Type: cross Abstract: PAC-Bayesian bounds provide finite-sample guarantees for data-dependent randomized predictors, but applying them to learning-based control is difficult because the natural objective is a quadratic trajectory cost.

By Domagoj Herceg
arXiv Machine Learning
Jun 8

Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments

arXiv:2606. 06855v1 Announce Type: cross Abstract: While algorithmic stability is a central tool for understanding generalization of learning algorithms, existing high-probability guarantees typically rely on uniform boundedness or sub-Gaussian/sub-Weibull tail assumptions, which can be overly restrictive for modern settings with heavy-tailed or unbounded losses.

By Qianqian Lei, Soham Bonnerjee, Yuefeng Han, Wei Biao Wu