mlsanityData to 7 Oct 2026

Confidence Threshold Neural Diving

arXiv 2202.07506 ↗First posted 15 Feb 2022math.OC cs.AI cs.DMcited by 5

Not on the map. Why?

Abstract (arXiv)

Finding a better feasible solution in a shorter time is an integral part of solving Mixed Integer Programs. We present a post-hoc method based on Neural Diving to build heuristics more flexibly. We hypothesize that variables with higher confidence scores are more definite to be included in the optimal solution. For our hypothesis, we provide empirical evidence that confidence threshold technique produces partial solutions leading to final solutions with better primal objective values. Our method won 2nd place in the primal task on the NeurIPS 2021 ML4CO competition. Also, our method shows the best score among other learning-based methods in the competition.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 11 of its 16 references that are in the map. First posted on arXiv 15 Feb 2022.

Builds on

11 of 16 references.

References · 11

  1. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  2. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 313
  3. 2020Solving Mixed Integer Programs Using Neural Networkscited by 178
  4. 2019Reinforcement Learning for Integer Programming: Learning to Cutcited by 108
  5. 2020Hybrid Models for Learning to Branchcited by 95
  6. 2020Parameterizing Branch-and-Bound Search Trees to Learn Branching Policiescited by 62
  7. 2021CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraintscited by 49
  8. 2021Learning to Select Cuts for Efficient Mixed-Integer Programmingcited by 48
  9. 2021Learning a Large Neighborhood Search Algorithm for Mixed Integer Programscited by 41
  10. 2021Learning Primal Heuristics for Mixed Integer Programscited by 14
  11. 2021Smart Feasibility Pump: Reinforcement Learning for (Mixed) Integer Programmingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programmingcited by 16
  2. 2025PROPEL: Supervised and Reinforcement Learning for Large-Scale Supply Chain Planningcited by 4
  3. 2024RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear Programscited by 1
  4. 2025HyP-ASO: A Hybrid Policy-based Adaptive Search Optimization Framework for Large-Scale Integer Linear Programscited by 0
  5. 2026Solving Integer Linear Programming with Parallel Temperingcited by 0