Taiji Suzuki

Artificial Intelligence · 2008–2021

A researcher in the Science corpus: 17 papers; trusts 616 researchers and is trusted by 57 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 307 citations into it; #5,565 of 35,345 by trust here, #8,439 by citations
• Computer Vision and Pattern Recognition — 155 citations into it; #6,286 of 21,575 by trust here, #8,205 by citations
• Statistics and Probability — 113 citations into it; #4,671 of 12,932 by trust here, #7,165 by citations
• Statistical Learning Theory — 102 citations into it
• Optimization & Training — 84 citations into it; #1,030 of 2,601 by trust here, #2,162 by citations
• Scaling & Learning Theory — 77 citations into it
• Model Architectures — 63 citations into it
• Computational Mechanics — 47 citations into it; #3,254 of 10,001 by trust here, #6,041 by citations

Whom Taiji Suzuki trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Shai Shalev-Shwartz
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Yoshua Bengio
5. Kaiming He
6. Tong Zhang
7. Yann LeCun
8. Shun-ichi Amari
9. Peter L. Bartlett
10. Andrew R. Barron

Who trusts Taiji Suzuki overall

1. Masashi Sugiyama
2. Mark W. Schmidt
3. Zhuoran Yang
4. Balaji Lakshminarayanan
5. Praneeth Vepakomma
6. Makoto Yamada
7. Huihui Wang
8. Song Liu
9. David Lopez-Paz
10. Takafumi Kanamori

Papers from Taiji Suzuki's perspective

Ordered by how strongly the researchers Taiji Suzuki trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. ImageNet: A large-scale hierarchical image database
6. Long Short-Term Memory
7. Attention is All you Need (Neural Information Processing Systems)
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Density Ratio Estimation in Machine Learning (2012) — 696 citations
• Direct importance estimation for covariate shift adaptation (2008) — 498 citations
• Sufficient Dimension Reduction via Squared-Loss Mutual Information Estimation (2010) — 115 citations
• Least-squares two-sample test (2011) — 45 citations
• A Scaling Law for Syn2real Transfer: How Much Is Your Pre-training Effective? (2021) — 17 citations
• Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint (2020) — 78 citations
• Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems (2019) — 43 citations
• Decomposable-Net: Scalable Low-Rank Compression for Neural Networks (2019) — 10 citations
• Graph Neural Networks Exponentially Lose Expressive Power for Node Classification (2019) — 917 citations
• Refined Generalization Analysis of Gradient Descent for Over-parameterized Two-layer Neural Networks with Smooth Activations on Classification Problems (2019) — 16 citations
• Cross-domain Recommendation via Deep Domain Adaptation (2018) — 99 citations
• Spectral-Pruning: Compressing deep neural network via spectral analysis (2018) — 12 citations
• Functional Gradient Boosting based on Residual Network Perception (2018) — 30 citations
• Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality (2018) — 300 citations
• Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers (2014) — 68 citations
• Spectral norm of random tensors (2014) — 68 citations
• Conditional Density Estimation via Least-Squares Density Ratio Estimation (2010) — 72 citations