Yusuke Tsuzuku

3 papers · 2018–2020 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird

Venues

CVPR (1) ICML (1) NeurIPS (1)

Top co-authors

Issei Sato (3) Masashi Sugiyama (2)

Research topics

Machine Learning (3) Deep Learning (2) Optimization & Theory · Machine Learning (2) Artificial Intelligence (1) Architectures (1) Core AI (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

adversarial perturbation (2) fourier analysis (1) neural network optimization (1) generalization error (1) pac-bayesian analysis (1) generalization bound (1) convolutional neural network (1) convolutional network (1) generalization guarantee (1) lipschitz constant (1) neural network robustness (1) flat minima (1) fourier basis (1) neural network generalization (1) pac-bayesian theory (1) universal adversarial perturbation (1) shift invariance (1) provable defense (1) scale invariance (1) neural network (1)

Papers

Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis ICML 2020 On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions CVPR 2019 Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks NeurIPS 2018