Yuka Hashimoto

Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs

Why and When Deep is Better than Shallow: An Implementation-Agnostic State-Transition View of Depth Supremacy

Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines

Deep Koopman-layered Model with Universal Property Based on Toeplitz Matrices

Spectral Truncation Kernels: Noncommutativity in $C^*$-algebraic Kernel Machines

Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines