AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Learning Energy Networks with Generalized Fenchel-Young Losses

Mathieu Blondel, Felipe Llinares-López, Robert Dadashi, Leonard Hussenot, Matthieu Geist

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 1 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
Add pairwise label interactions instead of using the unary linear modelGeneralized Fenchel-Young energy networks · yeasttest accuracy (%): 79.76 -> 80.19Improved
Add pairwise label interactions instead of using the unary linear modelGeneralized Fenchel-Young energy networks · scenetest accuracy (%): 89.14 -> 91.58Improved
Add pairwise label interactions instead of using the unary linear modelGeneralized Fenchel-Young energy networks · mediamilltest accuracy (%): 96.84 -> 96.95Improved
Add pairwise label interactions instead of using the unary linear modelGeneralized Fenchel-Young energy networks · birdstest accuracy (%): 86.47 -> 91.55Improved
Add pairwise label interactions instead of using the unary linear modelGeneralized Fenchel-Young energy networks · emotionstest accuracy (%): 78.22 -> 80.56Improved
Add pairwise label interactions instead of using the unary linear modelGeneralized Fenchel-Young energy networks · cal500test accuracy (%): 85.67 -> 85.73Improved
Make the SPEN prior energy concave in the outputSPEN · yeasttest accuracy (%): 79.99 -> 80.00No clear effect
Make the SPEN prior energy concave in the outputSPEN · scenetest accuracy (%): 91.24 -> 90.64Hurt
Make the SPEN prior energy concave in the outputSPEN · mediamilltest accuracy (%): 96.68 -> 96.95Improved
Make the SPEN prior energy concave in the outputSPEN · birdstest accuracy (%): 91.41 -> 91.77Improved
Make the SPEN prior energy concave in the outputSPEN · emotionstest accuracy (%): 79.35 -> 79.73Improved
Make the SPEN prior energy concave in the outputSPEN · cal500test accuracy (%): 86.25 -> 86.35Improved

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