Sufficient Dimension Reduction via Squared-Loss Mutual Information Estimation
By Taiji Suzuki, Masashi Sugiyama. 2010
115 citations recorded by the source corpus.
Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Statistics and Probability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
- Takafumi Kanamori
- Teruyuki Suzuki
- Makoto Yamada
- Ahmed M. Elgammal
- Chetan Tonde
- Praneeth Vepakomma
- Jun Takagi
- Gang Niu
In Computer Vision and Pattern Recognition
- Trevor Darrell
- Zeynep Akata
- Sayna Ebrahimi
- Ahmed M. Elgammal
- Jocelyn Chanussot
- Luc Van Gool
- Bernt Schiele
- Samarth Sinha
In Statistics and Probability
- Masashi Sugiyama
- Makoto Yamada
- Teruyuki Suzuki
- Takafumi Kanamori
- Voot Tangkaratt
- Tingting Zhao
- Syogo Mori
- Jun Morimoto
Citations in the corpus
- Supervised Dimensionality Reduction via Distance Correlation Maximization (2016, methodology): “Method/dimension 3 5 7 9 11 DisCoMax 0.1559 0.1493 0.1327 0.1311 0.1297 LSDR [Suzuki and Sugiyama, 2013] 0.1978 0.1963 0.1892 0.1886 0.1873 gKDR [Fukumizu and Leng, 2014] 0.1997 0.1813 0.1762 0.1738 0.1719 SCA [Yamada et al., 2011] 0.1875 0.1796 0.1708 0.1637 0.1602 LAD [Cook and Forzani, 2009] 0.20”
- Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders (2018, methodology): “DMAE aligns distributions by means of minimizing the Squared-Loss Mutual Information [28].”
- Feature Extraction for Hyperspectral Imagery: The Evolution From Shallow to Deep: Overview and Toolbox (2020, methodology): “[82], and JPlay [87]), and five techniques from the deep FE”
- Sufficient Component Analysis for Supervised Dimension Reduction (2011, methodology): “Suzuki & Sugiyama (2010) showed that the optimal transformation matrix that leads to Eq.”
- Density-ratio matching under the Bregman divergence: a unified framework of density-ratio estimation (2012, methodology): “, in identifying the central subspace in sufficient dimension reduction (Suzuki and Sugiyama 2010), finding independent components in independent component analysis (Suzuki and Sugiyama 2011), performing dependence-minimizing regression in causality learning (Yamada and Sugiyama 2010), and identifyi”
- Model-Based Policy Gradients with Parameter-Based Exploration by Least-Squares Conditional Density Estimation (2013, methodology): “For example, the use of the information-based method called least-squares dimension reduction (Suzuki and Sugiyama, 2013) before estimating the transition model by LSCDE will be investigated in our future work.”