AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Learning with Algorithmic Supervision via Continuous Relaxations

Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen

NeurIPS 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Gradient estimation for discrete variables · 5 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
Train with relaxed Bubble Sort rather than a task-specific sorting relaxationsorting supervision · 4-digit MNIST sorting, n=3, n=5, and n=7exact matches: 0.928 -> 0.944; 0.811 -> 0.842; 0.656 -> 0.707Improved
Use the relaxed Bellman-Ford algorithm instead of Perturbed Opt.Warcraft shortest-path supervision · Warcraft shortest-pathcost ratio: 1.00042 -> 1.00014Improved
Use the relaxed Bellman-Ford algorithm instead of Perturbed Opt.Warcraft shortest-path supervision · Warcraft shortest-pathexact match (EM): 91.7% -> 88.4%Hurt
Replace SoftRas with the relaxed silhouette renderersingle-view ShapeNet reconstruction · ShapeNet, batch size 2mean 3D IoU: 0.5455 -> 0.5256; 0.5455 -> 0.5349Hurt
Use relaxed Levenshtein distance supervision instead of the L1-encoding baselineEMNIST character classification · AB, BC, CD, DE, EF, IL, OX, ACGT, OSXLTop-1 accuracy: .616 -> .671; .651 -> .807; .768 -> .816; .739 -> .833; .701 -> .847; .550 -> .570; .893 -> .960; .403 -> .437; .448 -> Improved
Use relaxed Levenshtein distance supervision instead of the L1-encoding baselineEMNIST character classification · AB, BC, CD, DE, EF, IL, OX, ACGT, OSXLF1-score: .581 -> .666; .629 -> .805; .759 -> .815; .711 -> .831; .674 -> .845; .490 -> .539; .890 -> .960; .336 -> .367; .384 -> Improved
Use the directed Euclidean distance renderer instead of the three-edge renderer (ablation)relaxed silhouette supervision · ShapeNet, batch size 2mean 3D IoU: 0.5256 -> 0.5349Improved
Use the three-edge renderer instead of the directed Euclidean distance renderer (ablation)relaxed silhouette supervision · ShapeNet, batch size 2runtime: faster by a factor of 3Improved

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