3 papers
stat.ML2026
Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers
Mana Sakai, Masaaki Imaizumi
Understanding why trained Transformers generalize well is a fundamental problem in modern machine learning theory, and complexity-based generalization bounds provide a principled w…
cs.LG2026
Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
Mana Sakai, Ryo Karakida, Masaaki Imaizumi
In modern theoretical analyses of neural networks, the infinite-width limit is often invoked to justify Gaussian approximations of neuron preactivations (e.g., via neural network G…
math.ST2025
Priors for second-order unbiased Bayes estimators
Mana Sakai, Takeru Matsuda, Tatsuya Kubokawa
Asymptotically unbiased priors, introduced by Hartigan (1965), are designed to achieve second-order unbiasedness of Bayes estimators. This paper extends Hartigan's framework to non…