AI Paper Atlas

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

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 7 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Tiny ReLU verification · Tiny ReLUAverage bound: 13.7 -> 5.68Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Small ReLU verification · Small ReLUAverage bound: 544 -> 434.9Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Medium ReLU verification · Medium ReLUAverage bound: 1.6e+6 -> 1.5e+6Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Tiny SoftPlus verification · Tiny SoftPlusAverage bound: 13.7 -> 5.97Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Small SoftPlus verification · Small SoftPlusAverage bound: 5.1e+3 -> 3.93e+3Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Medium SoftPlus verification · Medium SoftPlusAverage bound: 1.5e+9 -> 1.3e+9Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Tiny ReLU verification · Tiny ReLURuntime (ms): 349 -> 91.2Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Small ReLU verification · Small ReLURuntime (ms): 711 -> 177Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Medium ReLU verification · Medium ReLURuntime (ms): 1.1e+3 -> 175Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Tiny SoftPlus verification · Tiny SoftPlusRuntime (ms): 414 -> 7.8Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Small SoftPlus verification · Small SoftPlusRuntime (ms): 855 -> 65Improved
Use the NonConvex staged reformulation and projected-gradient solver instead of DeepVerifyCIFAR-10 Medium SoftPlus verification · Medium SoftPlusRuntime (ms): 1.7e+3 -> 214Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy