AI Paper Atlas

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

An efficient, provably optimal, practical algorithm for the 0-1 loss linear classification problem

Xi He, Max A Little

ICLR 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Predict-then-optimize learning

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
exact 0-1 loss solver (ICE) instead of SVMlinear classifier · UCI HAtraining accuracy (%): 72.08 -> 77.03Improved
exact 0-1 loss solver (ICE) instead of SVMlinear classifier · UCI SPtraining accuracy (%): 94.05 -> 94.46Improved
exact solution instead of approximatelinear classifier · UCI HA, 5-fold testtest accuracy (%): 71.23 -> 74.39Improved
exact solution instead of SVMlinear classifier · UCI CR, 5-fold testtest accuracy (%): 85.56 -> 83.33Hurt
exact solution instead of approximatelinear classifier · UCI datasets (5-fold test)test accuracyMixed
ICE instead of BnB for 0-1 LCPexact solver · synthetic N=150, D=3wall-clock time: 1.2 seconds vs 10^10 secondsImproved
exact quadratic ICE instead of degree-2 SVMquadratic classifier · synthetic quadratic data0-1 loss: 17 -> 9Improved
MIP solver (GLPK) vs ICE and BnBexact solver · synthetic 3D datarun timeHurt

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