4 citations · 7 across the 6 of their papers we have counts for
7 papers
Neural Dimensional Analysis: Foundations of Dimensionless and Scale-Consistent Computation
Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa +1
Modern Transformers rely on many scale-control mechanisms, including normalization, residual scaling, attention temperatures, loss weighting, and adaptive updates. To explain how t…
QuadNorm: Resolution-Robust Normalization for Neural Operators
Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa +1
Normalization layers in neural operators usually compute statistics by uniformly averaging discrete grid values, making the normalization itself discretization-dependent and thereb…
Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability
Bum Jun Kim, Shohei Taniguchi, Makoto Kawano +2
Training divergence in transformers wastes compute, yet practitioners discover instability only after expensive runs begin. They therefore need an expected probability of failure f…
Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models
Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa +1
While the robustness of vision models is often measured, their dependence on specific architectural design choices is rarely dissected. We investigate why certain vision architectu…
Equivariant and Invariant Reynolds Networks
Akiyoshi Sannai, Makoto Kawano, Wataru Kumagai
Invariant and equivariant networks are useful in learning data with symmetry, including images, sets, point clouds, and graphs. In this paper, we consider invariant and equivariant…
Group Equivariant Conditional Neural Processes
Makoto Kawano, Wataru Kumagai, Akiyoshi Sannai +2
We present the group equivariant conditional neural process (EquivCNP), a meta-learning method with permutation invariance in a data set as in conventional conditional neural proce…
Improved Generalization Bounds of Group Invariant / Equivariant Deep Networks via Quotient Feature Spaces
Akiyoshi Sannai, Masaaki Imaizumi, Makoto Kawano
Numerous invariant (or equivariant) neural networks have succeeded in handling invariant data such as point clouds and graphs. However, a generalization theory for the neural netwo…