RIKEN Center for Advanced Intelligence Project Deep Learning Theory Team
Team Leader: Taiji Suzuki (Ph.D.)
Our team, deep learning theory team, is studying various kinds of learning systems including deep learning from theoretical viewpoints. We enrich our understandings of complex learning systems, and leverage the insights to construct new machine learning techniques and apply them. Especially, machine learning should deal with high dimensional and complicated data, and thus we are studying deep learning and structured sparse learning as methods to deal with such complicated data. Moreover, we are also developing efficient optimization algorithms for large and complicated machine learning problems based on such techniques as stochastic optimization.
Main Research Fields
- Computer Science
Related Research Fields
- Statistical learning theory of wide range of learning systems including deep learning
- Efficient optimization algorithm for large dataset
- High dimensional statistics
Papers with an asterisk(*) are based on research conducted outside of RIKEN.
- 1.*Suzuki, T., Kanagawa, H., Kobayashi, H., Shimizu, N., and Tagami, Y.:
"Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning"
The 30th Annual Conference on Neural Information Processing Systems (NIPS2016), pp. 3783-3791, (2016).
- 2.*Kanagawa, H., Suzuki, T., Kobayashi, H., Shimizu, N., and Tagami, Y.:
"Gaussian process nonparametric tensor estimator and its minimax optimality"
The 33rd International Conference on Machine Learning (ICML2016), pp. 1632–1641, (2016).
- 3.*Suzuki, T.:
"Convergence rate of Bayesian tensor estimator and its minimax optimality"
The 32nd International Conference on Machine Learning (ICML2015), pp. 1273-1282, (2015).
- 4.*Suzuki, T.:
"Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers" International Conference on Machine Learning (ICML2014), pp. 736--744, (2014).
- 5.*Tomioka, R., and Suzuki, T.:
"Convex Tensor Decomposition via Structured Schatten Norm Regularization"
Advances in Neural Information Processing Systems (NIPS2013), pp. 1331-1339, (2013).
- 6.*Suzuki, T.:
Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier Method.
International Conference on Machine Learning (ICML2013), pp. 392-400, (2013).
- 7.*Suzuki, T.:
"PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additive Model" Conference on Learning Theory (COLT2012), JMLR Workshop and Conference Proceedings 23: 8.1--8.20, (2012).
- 8.*Suzuki, T., and Sugiyama, M.:
"Fast learning rate of multiple kernel learning: trade-off between sparsity and smoothness"
The Annals of Statistics, vol. 41, number 3, pp. 1381-1405, (2013).
- Taiji Suzuki
- Team Leader
- Sho Sonoda
- Postdoctoral Researcher
Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo
Hongo 7-3-1, Bunkyo-ku, Tokyo 113-8656, JAPAN
Email: taiji [at] mist.i.u-tokyo.ac.jp