World's Best Scientists 2026 revealed!
Taiji Suzuki

Taiji Suzuki

D-Index & Metrics

Engineering and Technology

D-Index
37
Citations
5978
World Ranking
8355
National Ranking
176

Overview

Taiji Suzuki is affiliated with the University of Tokyo in Japan and has contributed extensively to the field of Computer Science, particularly focusing on areas within Artificial Intelligence and Statistics. Their work has been published primarily in the venue arXiv (Cornell University), with additional publications in the Electronic Journal of Statistics, Journal of Statistical Mechanics Theory and Experiment, Computational Statistics & Data Analysis, and the 2021 IEEE Symposium Series on Computational Intelligence.

Suzuki's research covers a broad spectrum of topics, including:

  • Stochastic Gradient Optimization Techniques
  • Sparse and Compressive Sensing Techniques
  • Model Reduction and Neural Networks
  • Domain Adaptation and Few-Shot Learning
  • Markov Chains and Monte Carlo Methods
  • Machine Learning and Extreme Learning Machines (ELM)
  • Neural Networks and Applications

Frequent collaborators include Atsushi Nitanda, Denny Wu, Kazusato Oko, Wei Huang, and Chihiro Watanabe, reflecting a consistent pattern of joint research efforts yielding multiple coauthored works.

Key recent papers authored or coauthored by Suzuki include:

  • "Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning," 2021, arXiv (Cornell University)
  • "When Does Preconditioning Help or Hurt Generalization?," 2020, arXiv (Cornell University)
  • "High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation," 2022, arXiv (Cornell University)
  • "Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space," 2021, Electronic Journal of Statistics
  • "Understanding Generalization in Deep Learning via Tensor Methods," 2020, arXiv (Cornell University)

Their work frequently addresses theoretical and practical challenges in machine learning, with a focus on optimization methods and generalization behavior in deep learning frameworks. The range of publication venues and collaborative partnerships indicates active engagement in both the theoretical foundations and computational practices related to contemporary statistical learning and artificial intelligence research.

Best Publications

  • Direct importance estimation for covariate shift adaptation

    Masashi Sugiyama;Taiji Suzuki;Shinichi Nakajima;Hisashi Kashima

  • Density Ratio Estimation in Machine Learning

    Masashi Sugiyama;Taiji Suzuki;Takafumi Kanamori

  • Graph Neural Networks Exponentially Lose Expressive Power for Node Classification

    Kenta Oono;Taiji Suzuki

  • Sufficient dimension reduction via squared-loss mutual information estimation

    Taiji Suzuki;Masashi Sugiyama

  • An experimental study of the martensite nucleation and growth in 18/8 stainless steel

    T Suzuki;H Kojima;K Suzuki;T Hashimoto

  • Density-ratio matching under the Bregman divergence: a unified framework of density-ratio estimation

    Masashi Sugiyama;Taiji Suzuki;Takafumi Kanamori

  • Statistical Performance of Convex Tensor Decomposition

    Ryota Tomioka;Taiji Suzuki;Kohei Hayashi;Hisashi Kashima

  • Relative Density-Ratio Estimation for Robust Distribution Comparison

    Makoto Yamada;Taiji Suzuki;Takafumi Kanamori;Hirotaka Hachiya

  • Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier Method

    Taiji Suzuki

  • Mutual information estimation reveals global associations between stimuli and biological processes.

    Taiji Suzuki;Masashi Sugiyama;Takafumi Kanamori;Jun Sese

  • Graph Neural Networks Exponentially Lose Expressive Power for Node Classification.

    Kenta Oono;Taiji Suzuki

  • Sufficient Dimension Reduction via Squared-loss Mutual Information Estimation

    Taiji Suzuki;Masashi Sugiyama

  • Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality.

    Taiji Suzuki

  • Approximating mutual information by maximum likelihood density ratio estimation

    Taiji Suzuki;Masashi Sugiyama;Jun Sese;Takafumi Kanamori

  • Convex Tensor Decomposition via Structured Schatten Norm Regularization

    Ryota Tomioka;Taiji Suzuki

  • Statistical analysis of kernel-based least-squares density-ratio estimation

    Takafumi Kanamori;Taiji Suzuki;Masashi Sugiyama

  • Super-Linear Convergence of Dual Augmented Lagrangian Algorithm for Sparsity Regularized Estimation

    Ryota Tomioka;Taiji Suzuki;Masashi Sugiyama

  • Least-Squares Conditional Density Estimation

    Masashi Sugiyama;Masashi Sugiyama;Ichiro Takeuchi;Taiji Suzuki;Takafumi Kanamori

  • Orientation dependence of slip in tantalum single crystals

    S Takeughi;E Kuramoto;T Suzuki

  • Cross-Domain Recommendation via Deep Domain Adaptation

    Heishiro Kanagawa;Hayato Kobayashi;Nobuyuki Shimizu;Yukihiro Tagami

  • $f$ -Divergence Estimation and Two-Sample Homogeneity Test Under Semiparametric Density-Ratio Models

    T. Kanamori;T. Suzuki;M. Sugiyama

  • Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers

    Taiji Suzuki

  • Density-Difference Estimation

    Masashi Sugiyama;Takafumi Kanamori;Taiji Suzuki;Marthinus D. Plessis

Frequent Co-Authors

Ryota Tomioka
Ryota Tomioka Microsoft (United States)
Kenji Fukumizu
Kenji Fukumizu The Institute of Statistical Mathematics
Kazuyuki Aihara
Kazuyuki Aihara University of Tokyo
Jimmy Ba
Jimmy Ba University of Toronto
Hisashi Kashima
Hisashi Kashima Kyoto University
Akimichi Takemura
Akimichi Takemura Shiga University
Roger Grosse
Roger Grosse University of Toronto
Shun-ichi Amari
Shun-ichi Amari RIKEN Center for Brain Science
Hajime Asama
Hajime Asama University of Tokyo

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Best Scientists Citing Taiji Suzuki

Trending Scientists

Recently Published Articles