Jianhao Ma

6 papers · 2022–2025 · 5 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 · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ICLR (2) COLT (1) ICML (1) JMLR (1) NeurIPS (1)

Top co-authors

Salar Fattahi (4) Lin Xiao (1) Lingjun Guo (1) Zechun Liu (1) Aaron Defazio (1) Lisa Jin (1) Andrey Gromov (1) Jiaye Teng (1) Yang Yuan (1)

Research topics

Machine Learning (6) Optimization & Theory · Machine Learning (6) Deep Learning (4) Optimization & Theory · Deep Learning (4) Core Methods (2) Artificial Intelligence (1) Mathematics & Optimization (1) Core AI (1) Optimization (1) Techniques (1)

Keywords

low-rank matrix (2) subgradient method (2) gradient descent (2) convergence guarantee (2) neural network (2) global convergence (2) matrix recovery (1) generalization bound (1) deep neural network (1) convolutional network (1) training stability (1) straight-through estimator (1) proximal stochastic gradient (1) quantization-aware training (1) neural network depth (1) flat minimum (1) transformer model (1) conjugate kernel (1) flat landscape (1) leave-one-out analysis (1)

Papers

PARQ: Piecewise-Affine Regularized Quantization ICML 2025 Convergence of Gradient Descent with Small Initialization for Unregularized Matrix Completion COLT 2024 Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition ICLR 2023 Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization JMLR 2023 Blessing of Depth in Linear Regression: Deeper Models Have Flatter Landscape Around the True Solution NeurIPS 2022 Towards Understanding Generalization via Decomposing Excess Risk Dynamics ICLR 2022