Qinghua Tao

6 papers · 2022–2024 · 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

NeurIPS (3) ICML (2) ICLR (1)

Top co-authors

Francesco Tonin (3) Xiaolin Huang (3) Yingyi Chen (3) Johan Suykens (3) Zhehao Huang (2) Yingwen Wu (2) Kexin Lv (1) jie Yang (1) Panagiotis Patrinos (1) Kun Fang (1)

Research topics

Machine Learning (6) Core Methods (3) Optimization & Theory (3) Deep Learning (2) Architectures (2) Learning Types (2) Artificial Intelligence (1) Mathematics & Optimization (1) Application Areas (1) Core AI (1) Mathematics (1) Techniques (1)

Keywords

singular value decomposition (2) principal component analysis (1) kernel principal component analysis (1) model robustness (1) model architecture (1) low-rank approximation (1) kernel pca (1) reconstruction error (1) distributed training (1) training efficiency (1) empirical evaluation (1) non-linear mapping (1) nyström method (1) adversarial attack (1) adversarial defense (1) out-of-distribution detection (1) weight averaging (1) evidence lower bound (1) self attention (1) kernel machine (1)

Papers

Kernel PCA for Out-of-Distribution Detection NeurIPS 2024 Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method ICML 2024 Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes ICML 2024 Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation NeurIPS 2023 Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions ICLR 2023 Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks NeurIPS 2022