Shiyun Xu

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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

AISTATS (2) ICLR (1) NeurIPS (1)

Top co-authors

Zhiqi Bu (4) Jialin Mao (1) Kan Chen (1)

Research topics

Deep Learning (4) Machine Learning (4) Optimization & Theory · Deep Learning (3) Architectures (2) Optimization & Theory · Machine Learning (2) Techniques (2) Security & Privacy (1) Application Areas (1) Core Methods (1) Differential Privacy (1) Learning Types (1)

Keywords

overparameterized neural network (2) convergence acceleration (1) neural tangent kernel (1) stochastic gradient descent (1) vision transformer (1) feature selection (1) model architecture (1) deep learning (1) neural network optimization (1) efficient computing (1) gradient descent (1) hessian matrix (1) learning rate (1) optimization algorithm (1) dynamical system (1) convergence rate (1) convolutional neural network (1) model training (1) gradient clipping (1) private training (1)

Papers

Gradient descent with generalized Newton’s method ICLR 2025 Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy NeurIPS 2022 A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks AISTATS 2021 DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks AISTATS 2021