Kazuki Uematsu

According to our database, Kazuki Uematsu authored at least 3 papers between 2015 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2024

Dimensionality-Induced Information Loss of Outliers in Deep Neural Networks.

Kazuki Uematsu, Kosuke Haruki, Taiji Suzuki, Mitsuhiro Kimura, Takahiro Takimoto, Hideyuki Nakagawa

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2024

2022

Data-Parallel Momentum Diagonal Empirical Fisher (DP-MDEF):Adaptive Gradient Method is Affected by Hessian Approximation and Multi-Class Data.

Chenyuan Xu, Kosuke Haruki, Taiji Suzuki, Masahiro Ozawa, Kazuki Uematsu, Ryuji Sakai

Proceedings of the 21st IEEE International Conference on Machine Learning and Applications, 2022

2015

Statistical Optimality in Multipartite Ranking and Ordinal Regression.

Kazuki Uematsu, Yoonkyung Lee

IEEE Trans. Pattern Anal. Mach. Intell., 2015