Kaixin Gao

4 papers · 2021–2025 · 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 (11) 🐣 Hot Topic Early Bird

Venues

AAAI (2) IJCAI (1) NeurIPS (1)

Top co-authors

Xiaolei Liu (3) Zhenghai Huang (2) Min Wang (2) Zidong Wang (2) Fan Yu (2) Dachuan Xu (2) Ningxi Ni (1) Fang Qu (1) Youyu Luo (1) Mengyun Chen (1)

Research topics

Machine Learning (4) Deep Learning (3) Optimization & Theory · Machine Learning (3) Optimization & Theory · Deep Learning (3) Learning Types (2) Techniques (2) Artificial Intelligence (1) Application Areas (1) Architectures (1) Core AI (1)

Keywords

second-order optimization (3) fisher information matrix (3) neural network training (3) neural network optimization (2) natural gradient descent (2) kronecker product (1) real-time prediction (1) deep neural network (1) layer-wise learning rate (1) hardware acceleration (1) model optimization (1) kronecker factorization (1) curvature approximation (1) pedestrian crossing intention (1) progressive perturbation (1) stochastic gradient descent (1) kronecker-factored approximation (1) domain adaptation (1) incremental learning (1) natural gradient (1)

Papers

EfficientPIE: Real-Time Prediction on Pedestrian Crossing Intention with Sole Observation IJCAI 2025 A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks NeurIPS 2024 A Trace-restricted Kronecker-Factored Approximation to Natural Gradient AAAI 2021 THOR, Trace-based Hardware-driven Layer-Oriented Natural Gradient Descent Computation AAAI 2021