Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time
cs.LG, cs.DS
Submitted: 2021-12-14
Updated: 2026-11-16
Terminology
Sources
- Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks
- Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems
- A Sublinear Adversarial Training Algorithm
- A Faster Small Treewidth SDP Solver
- Training Overparametrized Neural Networks in Sublinear Time
- Improved Reconstruction for Fourier-Sparse Signals
- Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis