Unbiased Estimating Equation on Inverse Divergence and Its Conditions

no code implementations • 25 Apr 2024 • Masahiro Kobayashi, Kazuho Watanabe

For the loss function defined by the monotonically increasing function $f$ and inverse divergence, the conditions for the statistical model and function $f$ under which the estimating equation is unbiased are clarified.

Overfitting in quantum machine learning and entangling dropout

no code implementations • 23 May 2022 • Masahiro Kobayashi, Kouhei Nakaji, Naoki Yamamoto

The ultimate goal in machine learning is to construct a model function that has a generalization capability for unseen dataset, based on given training dataset.

BIG-bench Machine Learning Quantum Machine Learning

Unbiased Estimation Equation under $f$-Separable Bregman Distortion Measures

no code implementations • 23 Oct 2020 • Masahiro Kobayashi, Kazuho Watanabe

We discuss unbiased estimation equations in a class of objective function using a monotonically increasing function $f$ and Bregman divergence.

Multi-Decoder RNN Autoencoder Based on Variational Bayes Method

no code implementations • 29 Apr 2020 • Daisuke Kaji, Kazuho Watanabe, Masahiro Kobayashi

Clustering algorithms have wide applications and play an important role in data analysis fields including time series data analysis.

Clustering Time Series +1

Extendable NFV-Integrated Control Method Using Reinforcement Learning

no code implementations • 19 Dec 2019 • Akito Suzuki, Ryoichi Kawahara, Masahiro Kobayashi, Shigeaki Harada, Yousuke Takahashi, Keisuke Ishibashi

The NFV control method should also be extendable for adding new metrics or changing the combination of metrics.

reinforcement-learning Reinforcement Learning (RL)

Generalized Dirichlet-process-means for $f$-separable distortion measures

no code implementations • 31 Jan 2019 • Masahiro Kobayashi, Kazuho Watanabe

Therefore, it is vulnerable to outliers in data, and can cause large maximum distortion in clusters.

Clustering