AI Paper Atlas

Research map / Optimization / Optimizers

Stochastic Structured Prediction under Bandit Feedback

Artem Sokolov, Julia Kreutzer, Stefan Riezler, Christopher Lo

NeurIPS 2016 · Optimization › Optimizers · approach: Randomized gradient estimation · 12 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
Use pairwise preference learning with binary feedback instead of expected-loss or cross-entropy learningBandit structured prediction on SMT · SMT testBLEU: 0.267 -> 0.273; 0.271 -> 0.273Improved
Use pairwise preference learning with binary feedback rather than expected-loss or cross-entropy learningBandit structured prediction on SMT · SMTiterations to best development score: 370k -> 115k; 281k -> 115kImproved
Use expected-loss minimization rather than pairwise preference or cross-entropy learningBandit structured prediction on chunking · Chunking testF1: 0.914 -> 0.923; 0.891 -> 0.923Improved
Use pairwise preference learning with continuous feedback rather than expected-loss or cross-entropy learningBandit structured prediction on chunking · Chunkingiterations to best development score: 7.5M -> 4.7M; 5.9M -> 4.7MImproved
Use pairwise preference learning instead of cross-entropy minimizationBandit structured prediction · SMTsquared stochastic gradient norm: 3.04$_{\pm 0.02}$ -> 2.88e-4$_{\pm 3.40e-6}$ (PR(bin)); 3.04$_{\pm 0.02}$ -> 1.03e-8$_{\pm 2.91e-10}$ (PR(cont))Improved
Use pairwise preference learning instead of cross-entropy minimizationBandit structured prediction · Chunkingsquared stochastic gradient norm: 4.20$_{\pm 0.71}$ -> 7.71e-4$_{\pm 2.53e-4}$ (PR(bin)); 4.20$_{\pm 0.71}$ -> 5.99e-3$_{\pm 7.24e-4}$ (PR(cont))Improved
Use continuous rather than binary pairwise feedback (ablation)Pairwise preference learning · SMTsquared stochastic gradient norm: 2.88e-4$_{\pm 3.40e-6}$ -> 1.03e-8$_{\pm 2.91e-10}$Improved
Use continuous rather than binary pairwise feedback (ablation)Pairwise preference learning · Chunkingsquared stochastic gradient norm: 7.71e-4$_{\pm 2.53e-4}$ -> 5.99e-3$_{\pm 7.24e-4}$Hurt

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