AI Paper Atlas

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

From Sequential to Recursive: Enhancing Decision-Focused Learning with Bidirectional Feedback

Xinyu Wang, Jinxiao Du, Yiyang Peng, Wei Ma

AAAI 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Decision-focused optimization · 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
add decision feedback to the predictor (recursive R-DFL-I instead of sequential S-DFL)DFL · Newsvendor (small, n=10)RMSE: 12.245 -> 8.831Improved
add decision feedback to the predictor (recursive R-DFL-I instead of sequential S-DFL)DFL · Newsvendor (large, n=100)RMSE: 12.649 -> 9.327Improved
add decision feedback (R-DFL-U instead of S-DFL)DFL · Newsvendor (mid, n=50)RMSE: 12.536 -> 9.173Improved
add decision feedback (R-DFL-I instead of S-DFL)DFL · Bipartite matching (large, n=900)RMSE: 0.187 -> 0.171Improved
add decision feedback (R-DFL-U instead of S-DFL)DFL · Bipartite matching (small, n=16)RMSE: 0.408 -> 0.396Improved
add decision feedback (R-DFL-I instead of S-DFL)DFL with Transformer predictor · Newsvendor (large)RMSE: 14.040 -> 11.332Improved
add decision feedback (R-DFL-I instead of S-DFL)DFL with Transformer predictor · Bipartite matching (large)RMSE: 0.188 -> 0.166Improved
add decision feedback (R-DFL-I instead of S-DFL)DFL with LSTM predictor · Newsvendor (large)RMSE: 12.693 -> 10.104Improved
use implicit differentiation instead of explicit unrollingR-DFL · Bipartite matching (large)training time per epoch (s): 2704 -> 1867Improved
use implicit differentiation instead of explicit unrollingR-DFL · Bipartite matching (mid)training time per epoch (s): 432 -> 65Improved
use implicit differentiation instead of explicit unrollingR-DFL · Newsvendor (large, n=100)RMSE: 9.343 -> 9.327No clear effect
use implicit differentiation instead of explicit unrollingR-DFL · Bipartite matching (small, n=16)RMSE: 0.396 -> 0.398Hurt

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