Taiji Suzuki

4.3k total citations
96 papers, 1.8k citations indexed

About

Taiji Suzuki is a scholar working on Artificial Intelligence, Statistics and Probability and Computational Mechanics. According to data from OpenAlex, Taiji Suzuki has authored 96 papers receiving a total of 1.8k indexed citations (citations by other indexed papers that have themselves been cited), including 56 papers in Artificial Intelligence, 36 papers in Statistics and Probability and 32 papers in Computational Mechanics. Recurrent topics in Taiji Suzuki's work include Sparse and Compressive Sensing Techniques (32 papers), Statistical Methods and Inference (24 papers) and Neural Networks and Applications (13 papers). Taiji Suzuki is often cited by papers focused on Sparse and Compressive Sensing Techniques (32 papers), Statistical Methods and Inference (24 papers) and Neural Networks and Applications (13 papers). Taiji Suzuki collaborates with scholars based in Japan, United States and Canada. Taiji Suzuki's co-authors include Masashi Sugiyama, Takafumi Kanamori, Ryota Tomioka, Paul von Bünau, Motoaki Kawanabe, Hisashi Kashima, Shinichi Nakajima, Jun Sese, Hirotaka Hachiya and Makoto Yamada and has published in prestigious journals such as BMC Bioinformatics, The Annals of Statistics and Neural Computation.

In The Last Decade

Taiji Suzuki

89 papers receiving 1.7k citations

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Taiji Suzuki Japan 22 947 422 370 313 240 96 1.8k
Zhaosong Lu Canada 26 500 0.5× 388 0.9× 294 0.8× 1.1k 3.4× 167 0.7× 69 2.0k
Vladimir Koltchinskii United States 23 925 1.0× 374 0.9× 922 2.5× 624 2.0× 148 0.6× 52 2.1k
P. Tseng United States 12 592 0.6× 576 1.4× 245 0.7× 712 2.3× 238 1.0× 15 2.3k
Shinichi Nakajima Japan 17 1.0k 1.1× 580 1.4× 128 0.3× 147 0.5× 217 0.9× 105 2.0k
Rahul Mazumder United States 12 325 0.3× 283 0.7× 298 0.8× 425 1.4× 158 0.7× 36 1.3k
Guillaume Obozinski Switzerland 15 700 0.7× 588 1.4× 362 1.0× 795 2.5× 184 0.8× 38 2.0k
Marco Cuturi France 19 934 1.0× 885 2.1× 268 0.7× 300 1.0× 208 0.9× 45 2.6k
Yiming Ying United States 25 1.3k 1.3× 996 2.4× 240 0.6× 664 2.1× 229 1.0× 77 2.6k
Rodolphe Jenatton France 14 353 0.4× 418 1.0× 129 0.3× 523 1.7× 119 0.5× 19 1.1k

Countries citing papers authored by Taiji Suzuki

Since Specialization
Citations

This map shows the geographic impact of Taiji Suzuki's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Taiji Suzuki with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Taiji Suzuki more than expected).

Fields of papers citing papers by Taiji Suzuki

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Taiji Suzuki. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Taiji Suzuki. The network helps show where Taiji Suzuki may publish in the future.

Co-authorship network of co-authors of Taiji Suzuki

This figure shows the co-authorship network connecting the top 25 collaborators of Taiji Suzuki. A scholar is included among the top collaborators of Taiji Suzuki based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Taiji Suzuki. Taiji Suzuki is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Sato, Kanji, Akiko Takeda, Reiichiro Kawai, & Taiji Suzuki. (2024). Convergence error analysis of reflected gradient Langevin dynamics for non-convex constrained optimization. Japan Journal of Industrial and Applied Mathematics. 42(1). 127–151.
2.
Kobayashi, Kenichi, et al.. (2023). Neural Network Module Decomposition and Recomposition with Superimposed Masks. 7. 1–10. 1 indexed citations
3.
Suzuki, Taiji, et al.. (2022). Particle dual averaging: optimization of mean field neural network with global convergence rate analysis*. Journal of Statistical Mechanics Theory and Experiment. 2022(11). 114010–114010. 5 indexed citations
4.
Suzuki, Taiji, et al.. (2021). Bayesian optimization design for finding a maximum tolerated dose combination in phase I clinical trials. The International Journal of Biostatistics. 18(1). 39–56. 1 indexed citations
5.
Suzuki, Taiji, et al.. (2021). Bayesian optimization for estimating the maximum tolerated dose in Phase I clinical trials. Contemporary Clinical Trials Communications. 21. 100753–100753. 4 indexed citations
6.
Suzuki, Taiji, et al.. (2021). Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space. Neural Information Processing Systems. 34. 2 indexed citations
7.
Suzuki, Taiji, et al.. (2021). Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime. arXiv (Cornell University). 1 indexed citations
8.
Suzuki, Taiji. (2020). Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network. International Conference on Learning Representations. 1 indexed citations
9.
Oono, Kenta & Taiji Suzuki. (2020). Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks. Neural Information Processing Systems. 33. 18917–18930. 1 indexed citations
10.
Oono, Kenta & Taiji Suzuki. (2019). On Asymptotic Behaviors of Graph CNNs from Dynamical Systems Perspective. arXiv (Cornell University). 4 indexed citations
11.
Suzuki, Taiji, et al.. (2017). Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization. Neural Information Processing Systems. 30. 608–617. 4 indexed citations
12.
Suzuki, Taiji, et al.. (2017). Stochastic Difference of Convex Algorithm and its Application to Training Deep Boltzmann Machines. International Conference on Artificial Intelligence and Statistics. 470–478. 5 indexed citations
13.
Suzuki, Taiji, et al.. (2016). Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning. Neural Information Processing Systems. 29. 3783–3791. 2 indexed citations
14.
Suzuki, Taiji. (2013). Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier Method. International Conference on Machine Learning. 53(9). 392–400. 67 indexed citations
15.
Kanamori, Takafumi, Akiko Takeda, & Taiji Suzuki. (2013). Conjugate relation between loss functions and uncertainty sets in classification problems. Journal of Machine Learning Research. 14(1). 1461–1504. 9 indexed citations
16.
Suzuki, Taiji. (2012). PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additive Model. Conference on Learning Theory. 10 indexed citations
17.
Tomioka, Ryota, Taiji Suzuki, Kohei Hayashi, & Hisashi Kashima. (2011). Statistical Performance of Convex Tensor Decomposition. Neural Information Processing Systems. 24. 972–980. 71 indexed citations
18.
Suzuki, Taiji. (2011). Unifying Framework for Fast Learning Rate of Non-Sparse Multiple Kernel Learning. Neural Information Processing Systems. 24. 1575–1583. 8 indexed citations
19.
Tomioka, Ryota & Taiji Suzuki. (2010). Regularization Strategies and Empirical Bayesian Learning for MKL. IEICE Technical Report; IEICE Tech. Rep.. 110(265). 303–310. 1 indexed citations
20.
Tomioka, Ryota, Taiji Suzuki, Masashi Sugiyama, & Hisashi Kashima. (2010). A Fast Augmented Lagrangian Algorithm for Learning Low-Rank Matrices. International Conference on Machine Learning. 1087–1094. 15 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026