← Authors

Fanghui Liu

25 papers · 2020–2025 · 7 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (7) πŸƒ Academic Marathon (5) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (8) πŸ—ΊοΈ Taxonomy Completionist (28) 🀝 Dynamic Duo (17) πŸ† Grand Slam πŸ”¬ Deep Specialist (11) πŸ’Ž Century Club (25) ⚑ Prolific Year (8) πŸ—ƒοΈ Keyword Collector (69) ❓ The Questioner πŸ”₯ Unstoppable (6)

Conferences

NIPS (8) ICML (5) ICLR (4) JMLR (3) AAAI (2) AISTATS (2) ECCV (1)

Top co-authors

Volkan Cevher (17) Grigorios Chrysos (10) Zhenyu Zhu (6) Xiaolin Huang (5) Johan Suykens (4) Yongtao Wu (4) jie Yang (3) Elias Abad Rocamora (3) Yihang Chen (2) Yudong Chen (2)

Keywords

neural tangent kernel (5) generalization bound (5) neural network (4) kernel methods (4) function approximation (3) reproducing kernel hilbert space (3) kernel ridge regression (3) neural network robustness (2) barron space (2) double descent (2) regret bound (2) deep neural network (2) random feature (2) neural network optimization (1) neural architecture search (1) self-attention mechanism (1) sample complexity (1) global convergence (1) sample efficiency (1) reinforcement learning (1)

Papers

How Gradient descent balances features: A dynamical analysis for two-layer neural networks ICLR 2025
LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently ICML 2025
Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks JMLR 2024
The Role of Over-Parameterization in Machine Learning – the Good, the Bad, the Ugly AAAI 2024
Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy ECCV 2024
Generalization of Scaled Deep ResNets in the Mean-Field Regime ICLR 2024
Robust NAS under adversarial training: benchmark, theory, and beyond ICLR 2024
Efficient local linearity regularization to overcome catastrophic overfitting ICLR 2024
Revisiting Character-level Adversarial Attacks for Language Models ICML 2024
High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization ICML 2024
Benign Overfitting in Deep Neural Networks under Lazy Training ICML 2023
What can online reinforcement learning with function approximation benefit from general coverage conditions? ICML 2023
Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks NIPS 2023
On the Convergence of Encoder-only Shallow Transformers NIPS 2023
Sound and Complete Verification of Polynomial Networks NIPS 2022
Generalization Properties of NAS under Activation and Skip Connection Search NIPS 2022
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study NIPS 2022
On the Double Descent of Random Features Models Trained with SGD NIPS 2022
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) NIPS 2022
Understanding Deep Neural Function Approximation in Reinforcement Learning via $\epsilon$-Greedy Exploration NIPS 2022
Generalization Properties of hyper-RKHS and its Applications JMLR 2021
Fast Learning in Reproducing Kernel Krein Spaces via Signed Measures AISTATS 2021
Kernel regression in high dimensions: Refined analysis beyond double descent AISTATS 2021
Learning Data-adaptive Non-parametric Kernels JMLR 2020
Random Fourier Features via Fast Surrogate Leverage Weighted Sampling AAAI 2020