Research map / Optimization / Nonconvex and smooth optimization
An efficient nonconvex reformulation of stagewise convex optimization problems
Rudy R Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy Dvijotham
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 |
|---|---|---|---|
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Tiny ReLU verification · Tiny ReLU | Average bound: 13.7 -> 5.68 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Small ReLU verification · Small ReLU | Average bound: 544 -> 434.9 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Medium ReLU verification · Medium ReLU | Average bound: 1.6e+6 -> 1.5e+6 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Tiny SoftPlus verification · Tiny SoftPlus | Average bound: 13.7 -> 5.97 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Small SoftPlus verification · Small SoftPlus | Average bound: 5.1e+3 -> 3.93e+3 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Medium SoftPlus verification · Medium SoftPlus | Average bound: 1.5e+9 -> 1.3e+9 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Tiny ReLU verification · Tiny ReLU | Runtime (ms): 349 -> 91.2 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Small ReLU verification · Small ReLU | Runtime (ms): 711 -> 177 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Medium ReLU verification · Medium ReLU | Runtime (ms): 1.1e+3 -> 175 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Tiny SoftPlus verification · Tiny SoftPlus | Runtime (ms): 414 -> 7.8 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Small SoftPlus verification · Small SoftPlus | Runtime (ms): 855 -> 65 | Improved |
| Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerify | CIFAR-10 Medium SoftPlus verification · Medium SoftPlus | Runtime (ms): 1.7e+3 -> 214 | Improved |
Closest papers by meaning
- Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization (JMLR 2025 · similarity 0.88)
- General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization (ICML 2025 · similarity 0.88)
- Semi-infinite Nonconvex Constrained Min-Max Optimization (NeurIPS 2025 · similarity 0.88)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.87)
- Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization (ICML 2024 · similarity 0.87)
- Inexact Newton-type Methods for Optimisation with Nonnegativity Constraints (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.
