AI Paper Atlas

Research map / Optimization / Optimizers

Surfing: Iterative Optimization Over Incrementally Trained Deep Networks

Ganlin Song, Zhou Fan, John Lafferty

NeurIPS 2019 · Optimization › Optimizers · approach: Differentiating through embedded optimization · 6 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
Optimize sequentially across training checkpoints instead of only optimizing the final networkVAE · Fashion-MNIST generated recovery, input dimension 5solutions within 0.01 of true latent (%): 99.3 -> 99.3No clear effect
Optimize sequentially across training checkpoints instead of only optimizing the final networkDCGAN · Fashion-MNIST generated recovery, input dimension 5solutions within 0.01 of true latent (%): 50.3 -> 91.3Improved
Optimize sequentially across training checkpoints instead of only optimizing the final networkWGAN · Fashion-MNIST generated recovery, input dimension 5solutions within 0.01 of true latent (%): 48.3 -> 86.7Improved
Optimize sequentially across training checkpoints instead of only optimizing the final networkWGAN-GP · Fashion-MNIST generated recovery, input dimension 5solutions within 0.01 of true latent (%): 46.7 -> 92.0Improved
Use random initialization as the starting objective, then track the optimum while the network trainsSurfing · Fashion-MNIST generated recoverysolutions within 0.01 of true latent (%)Mixed

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