AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients

Anselm Paulus, Andreas René Geist, Vít Musil, Sebastian Hoffmann, Georg Martius

ICML 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Structure and complexity of constraint reasoning · 0 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
apply straight-through estimation to each function separately before multiplying (ablation)STE-wrapped relu product · relu(x)*relu(y) gradientgradient informativenessHurt
apply straight-through estimation to the composite function instead of each factor (ablation)STE-wrapped relu product · relu(x)*relu(y) gradientgradient informativenessImproved
use sorting network instead of other soft sort methodssj.sort smooth mode · n=4096 runtimetime (ms): 1.0 ms vs SoftSort 16 ms, NeuralSort 37 msImproved
use FastSoftSort instead of matrix-based soft sortssj.sort smooth mode · n=4096 memorypeak memory: 420 kB at n = 4096Improved
use SmoothSort or OT-based sortsj.sort smooth mode · n=4096 runtimetimeHurt
use soft abs inside NeuralSort instead of hard absNeuralSort · smoothnessdifferentiability at tiesImproved

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