Research map / Optimization / Implicit bias and generalization
Piecewise Strong Convexity of Neural Networks
Tristan Milne
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Restrict the regularized loss to SGD trajectories on MNIST | LeNet-5 · MNIST | loss fraction: 0.80 ± 0.09 | Improved |
| Restrict the regularized loss to SGD trajectories on CIFAR10 | ResNet22 · CIFAR10 | loss fraction: 1.00 ± 0.00 | Improved |
| Restrict the regularized loss to SGD trajectories on CIFAR100 | ResNet22 · CIFAR100 | loss fraction: 1.00 ± 0.02 | Improved |
| Train with gradient descent until entering U(lambda) | Toy regression network · Toy regression | loss-change fraction in U(lambda): 87.2% ± 22.3% | Improved |
Closest papers by meaning
- Piecewise linear activations substantially shape the loss surfaces of neural networks (ICLR 2020 · similarity 0.89)
- Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality (ICLR 2025 · similarity 0.89)
- Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time (ICML 2024 · similarity 0.87)
- Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation (ICML 2024 · similarity 0.87)
- SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures (NeurIPS 2025 · similarity 0.87)
- Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes (ICML 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
