Fangzhao Zhang

5 papers · 2023–2025 · 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)

Venues

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

Top co-authors

Mert Pilanci (5) Elad Romanov (1) Erica Zhang (1)

Research topics

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

Keywords

second-order optimization (2) newton method (2) distributed optimization (2) hessian approximation (1) low-rank matrix (1) random matrix theory (1) parameter-efficient fine-tuning (1) low-rank adaptation (1) randomized sketching (1) model efficiency (1) relu network (1) stochastic method (1) gradient step (1) convergence theory (1) feasible set (1) hessian sketching (1) spectral adapter (1) marchenko-pastur law (1) sgd (1) adamw (1)

Papers

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes ICML 2025 Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing ICLR 2025 Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models ICML 2024 Spectral Adapter: Fine-Tuning in Spectral Space NeurIPS 2024 Optimal Shrinkage for Distributed Second-Order Optimization ICML 2023