2 citations · 2 across the 4 of their papers we have counts for
6 papers
Normalized Maximum Likelihood Code-Length on Riemannian Data Spaces
Kota Fukuzawa, Atsushi Suzuki, Kenji Yamanishi
In recent years, with the large-scale expansion of graph data, there has been an increased focus on Riemannian manifold data spaces other than Euclidean space. In particular, the d…
Foundation of Calculating Normalized Maximum Likelihood for Continuous Probability Models
Atsushi Suzuki, Kota Fukuzawa, Kenji Yamanishi
The normalized maximum likelihood (NML) code length is widely used as a model selection criterion based on the minimum description length principle, where the model with the shorte…
Tight and fast generalization error bound of graph embedding in metric space
Atsushi Suzuki, Atsushi Nitanda, Taiji Suzuki +3
Recent studies have experimentally shown that we can achieve in non-Euclidean metric space effective and efficient graph embedding, which aims to obtain the vertices' representatio…
Generalization Error Bound for Hyperbolic Ordinal Embedding
Atsushi Suzuki, Atsushi Nitanda, Jing Wang +3
Hyperbolic ordinal embedding (HOE) represents entities as points in hyperbolic space so that they agree as well as possible with given constraints in the form of entity i is more s…
Stable Geodesic Update on Hyperbolic Space and its Application to Poincare Embeddings
Yosuke Enokida, Atsushi Suzuki, Kenji Yamanishi
A hyperbolic space has been shown to be more capable of modeling complex networks than a Euclidean space. This paper proposes an explicit update rule along geodesics in a hyperboli…
Exact Calculation of Normalized Maximum Likelihood Code Length Using Fourier Analysis
Atsushi Suzuki, Kenji Yamanishi
The normalized maximum likelihood code length has been widely used in model selection, and its favorable properties, such as its consistency and the upper bound of its statistical…