Timezone: »
Exponential family distributions are highly useful in machine learning since their calculation can be performed efficiently through natural parameters. The exponential family has recently been extended to the t-exponential family, which contains Student-t distributions as family members and thus allows us to handle noisy data well. However, since the t-exponential family is defined by the deformed exponential, an efficient learning algorithm for the t-exponential family such as expectation propagation (EP) cannot be derived in the same way as the ordinary exponential family. In this paper, we borrow the mathematical tools of q-algebra from statistical physics and show that the pseudo additivity of distributions allows us to perform calculation of t-exponential family distributions through natural parameters. We then develop an expectation propagation (EP) algorithm for the t-exponential family, which provides a deterministic approximation to the posterior or predictive distribution with simple moment matching. We finally apply the proposed EP algorithm to the Bayes point machine and Student-t process classification, and demonstrate their performance numerically.
Author Information
Futoshi Futami (University of Tokyo/RIKEN)
Issei Sato (The University of Tokyo/RIKEN)
Masashi Sugiyama (RIKEN / University of Tokyo)
More from the Same Authors
-
2020 Poster: Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning »
Yu Yao · Tongliang Liu · Bo Han · Mingming Gong · Jiankang Deng · Gang Niu · Masashi Sugiyama -
2020 Poster: Part-dependent Label Noise: Towards Instance-dependent Label Noise »
Xiaobo Xia · Tongliang Liu · Bo Han · Nannan Wang · Mingming Gong · Haifeng Liu · Gang Niu · Dacheng Tao · Masashi Sugiyama -
2020 Spotlight: Part-dependent Label Noise: Towards Instance-dependent Label Noise »
Xiaobo Xia · Tongliang Liu · Bo Han · Nannan Wang · Mingming Gong · Haifeng Liu · Gang Niu · Dacheng Tao · Masashi Sugiyama -
2020 Poster: Rethinking Importance Weighting for Deep Learning under Distribution Shift »
Tongtong Fang · Nan Lu · Gang Niu · Masashi Sugiyama -
2020 Poster: Learning from Aggregate Observations »
Yivan Zhang · Nontawat Charoenphakdee · Zhenguo Wu · Masashi Sugiyama -
2020 Poster: Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring »
Taira Tsuchiya · Junya Honda · Masashi Sugiyama -
2020 Spotlight: Rethinking Importance Weighting for Deep Learning under Distribution Shift »
Tongtong Fang · Nan Lu · Gang Niu · Masashi Sugiyama -
2020 Poster: Provably Consistent Partial-Label Learning »
Lei Feng · Jiaqi Lv · Bo Han · Miao Xu · Gang Niu · Xin Geng · Bo An · Masashi Sugiyama -
2020 Poster: Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators »
Takeshi Teshima · Isao Ishikawa · Koichi Tojo · Kenta Oono · Masahiro Ikeda · Masashi Sugiyama -
2020 Oral: Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators »
Takeshi Teshima · Isao Ishikawa · Koichi Tojo · Kenta Oono · Masahiro Ikeda · Masashi Sugiyama -
2019 Poster: Uncoupled Regression from Pairwise Comparison Data »
Liyuan Xu · Junya Honda · Gang Niu · Masashi Sugiyama -
2019 Poster: Are Anchor Points Really Indispensable in Label-Noise Learning? »
Xiaobo Xia · Tongliang Liu · Nannan Wang · Bo Han · Chen Gong · Gang Niu · Masashi Sugiyama -
2019 Poster: On the Calibration of Multiclass Classification with Rejection »
Chenri Ni · Nontawat Charoenphakdee · Junya Honda · Masashi Sugiyama -
2018 Poster: Binary Classification from Positive-Confidence Data »
Takashi Ishida · Gang Niu · Masashi Sugiyama -
2018 Spotlight: Binary Classification from Positive-Confidence Data »
Takashi Ishida · Gang Niu · Masashi Sugiyama -
2018 Poster: Uplift Modeling from Separate Labels »
Ikko Yamane · Florian Yger · Jamal Atif · Masashi Sugiyama -
2018 Poster: Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces »
Motoya Ohnishi · Masahiro Yukawa · Mikael Johansson · Masashi Sugiyama -
2018 Poster: Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks »
Yusuke Tsuzuku · Issei Sato · Masashi Sugiyama -
2018 Poster: Masking: A New Perspective of Noisy Supervision »
Bo Han · Jiangchao Yao · Gang Niu · Mingyuan Zhou · Ivor Tsang · Ya Zhang · Masashi Sugiyama -
2018 Poster: Co-teaching: Robust training of deep neural networks with extremely noisy labels »
Bo Han · Quanming Yao · Xingrui Yu · Gang Niu · Miao Xu · Weihua Hu · Ivor Tsang · Masashi Sugiyama -
2017 Poster: On the Model Shrinkage Effect of Gamma Process Edge Partition Models »
Iku Ohama · Issei Sato · Takuya Kida · Hiroki Arimura -
2017 Poster: Positive-Unlabeled Learning with Non-Negative Risk Estimator »
Ryuichi Kiryo · Gang Niu · Marthinus C du Plessis · Masashi Sugiyama -
2017 Poster: Learning from Complementary Labels »
Takashi Ishida · Gang Niu · Weihua Hu · Masashi Sugiyama -
2017 Oral: Positive-Unlabeled Learning with Non-Negative Risk Estimator »
Ryuichi Kiryo · Gang Niu · Marthinus C du Plessis · Masashi Sugiyama -
2017 Poster: Generative Local Metric Learning for Kernel Regression »
Yung-Kyun Noh · Masashi Sugiyama · Kee-Eung Kim · Frank Park · Daniel Lee -
2016 Poster: Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning »
Gang Niu · Marthinus Christoffel du Plessis · Tomoya Sakai · Yao Ma · Masashi Sugiyama -
2014 Poster: Analysis of Variational Bayesian Latent Dirichlet Allocation: Weaker Sparsity Than MAP »
Shinichi Nakajima · Issei Sato · Masashi Sugiyama · Kazuho Watanabe · Hiroko Kobayashi -
2014 Poster: Multitask learning meets tensor factorization: task imputation via convex optimization »
Kishan Wimalawarne · Masashi Sugiyama · Ryota Tomioka -
2014 Poster: Analysis of Learning from Positive and Unlabeled Data »
Marthinus C du Plessis · Gang Niu · Masashi Sugiyama -
2013 Poster: Parametric Task Learning »
Ichiro Takeuchi · Tatsuya Hongo · Masashi Sugiyama · Shinichi Nakajima -
2013 Poster: Global Solver and Its Efficient Approximation for Variational Bayesian Low-rank Subspace Clustering »
Shinichi Nakajima · Akiko Takeda · S. Derin Babacan · Masashi Sugiyama · Ichiro Takeuchi -
2012 Poster: Perfect Dimensionality Recovery by Variational Bayesian PCA »
Shinichi Nakajima · Ryota Tomioka · Masashi Sugiyama · S. Derin Babacan -
2012 Poster: Density-Difference Estimation »
Masashi Sugiyama · Takafumi Kanamori · Taiji Suzuki · Marthinus C du Plessis · Song Liu · Ichiro Takeuchi -
2011 Poster: Relative Density-Ratio Estimation for Robust Distribution Comparison »
Makoto Yamada · Taiji Suzuki · Takafumi Kanamori · Hirotaka Hachiya · Masashi Sugiyama -
2011 Poster: Target Neighbor Consistent Feature Weighting for Nearest Neighbor Classification »
Ichiro Takeuchi · Masashi Sugiyama -
2011 Poster: Analysis and Improvement of Policy Gradient Estimation »
Tingting Zhao · Hirotaka Hachiya · Gang Niu · Masashi Sugiyama -
2011 Poster: Global Solution of Fully-Observed Variational Bayesian Matrix Factorization is Column-Wise Independent »
Shinichi Nakajima · Masashi Sugiyama · S. Derin Babacan -
2010 Spotlight: Global Analytic Solution for Variational Bayesian Matrix Factorization »
Shinichi Nakajima · Masashi Sugiyama · Ryota Tomioka -
2010 Poster: Global Analytic Solution for Variational Bayesian Matrix Factorization »
Shinichi Nakajima · Masashi Sugiyama · Ryota Tomioka -
2008 Poster: Efficient Direct Density Ratio Estimation for Non-stationarity Adaptation and Outlier Detection »
Takafumi Kanamori · Shohei Hido · Masashi Sugiyama -
2007 Poster: Direct Importance Estimation with Model Selection and Its Application to Covariate Shift Adaptation »
Masashi Sugiyama · Shinichi Nakajima · Hisashi Kashima · Paul von Buenau · Motoaki Kawanabe -
2007 Poster: Multi-Task Learning via Conic Programming »
Tsuyoshi Kato · Hisashi Kashima · Masashi Sugiyama · Kiyoshi Asai -
2006 Workshop: Learning when test and training inputs have different distributions »
Joaquin QuiƱonero Candela · Masashi Sugiyama · Anton Schwaighofer · Neil D Lawrence -
2006 Poster: Mixture Regression for Covariate Shift »
Amos Storkey · Masashi Sugiyama