Reality Only Happens Once: Single-Path Generalization Bounds for Transformers

no code implementations • 26 May 2024 • Yannick Limmer, Anastasis Kratsios, Xuwei Yang, Raeid Saqur, Blanka Horvath

We derive non-asymptotic statistical guarantees in this setting through bounds on the \textit{generalization} of a transformer network at a future-time $t$, given that it has been trained using $N\le t$ observations from a single perturbed trajectory of a Markov process.

Generalization Bounds Transformer

Deep Kalman Filters Can Filter

no code implementations • 30 Oct 2023 • Blanka Hovart, Anastasis Kratsios, Yannick Limmer, Xuwei Yang

Deep Kalman filters (DKFs) are a class of neural network models that generate Gaussian probability measures from sequential data.

Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing

1 code implementation • 8 Sep 2023 • Xuwei Yang, Anastasis Kratsios, Florian Krach, Matheus Grasselli, Aurelien Lucchi

We propose an optimal iterative scheme for federated transfer learning, where a central planner has access to datasets ${\cal D}_1,\dots,{\cal D}_N$ for the same learning model $f_{\theta}$.

Adversarial Robustness regression +1