Author

Atsushi Nitanda

4 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Which Geometry on Which Layer? Measured Sign-Spectral Assignment in Mixed-Optimizer Training

Modern neural-network training uses mixed recipes, assigning AdamW-like or sign-based updates to embedding and output layers and spectral updates to hidden matrices. These assignments are usually fixed by layer type, without a clear criterion for selecting the appropriate geometry. We turn sign-versus-spectral assignme...

Hiroki Naganuma, Laura Gomezjurado, Mahdi Ghaznavi et al. · 0 citations

#machine learning Preprint Oct 2026

Finite-Sample Approximation of Hessian-Guided Perturbed Wasserstein Gradient Flows

Wasserstein gradient flow extends gradient descent to probability measures. Its Hessian-guided perturbed variant (PWGF) adds Gaussian perturbations to escape saddle points in nonconvex problems. We investigate when its approximation by finitely many interacting particles remains accurate over growing time horizons. Our...

Ryotaro Kawata, Atsushi Nitanda, Taiji Suzuki · 0 citations

#machine learning Preprint Oct 2026

Learning Decision-Stump Thresholds in Context: Dynamics of Softmax Attention

Estimating a decision threshold requires locating observations near an unknown boundary. We study how gradient-based pretraining learns this statistical rule in a two-parameter softmax-attention model with a fixed feature and inequality direction. Pretraining uses labeled contexts and their true thresholds; a fresh thr...

H. Lệ, Jackie Lok, Atsushi Nitanda et al. · 0 citations

#machine learning Preprint Oct 2026

Diffusion Transformers are Provably Optimal In-context Generators

Generative foundation models are attracting interest for their ability to produce desired outputs from demonstrations given at inference time, without updating parameters. However, since a few demonstrations cannot uniquely identify the intended task, the challenge is how to learn and sample from an output distribution...

Guoji Fu, Tomoya Wakayama, Ryotaro Kawata et al. · 0 citations