Research map / Graph learning / Graph algorithms and clustering
Beyond Binary: Continuous State Optimization with Graph-Structured Objectives
Corinna Cortes, Yishay Mansour, Mehryar Mohri
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace per-step LCB re-optimization with lazy determinant-doubling updates | LinUCB · Single-clique d=2, T=300 | cumulative movement cost: 22 -> 8 | Improved |
| lazy updates | LinUCB · Single-clique d=2, T=300 | cumulative prediction regret | No clear effect |
| asynchronous local updates instead of global synchronized lazy updates | Lazy Graph-LinUCB · Heterogeneous graph k=10 | total moves: 410 -> 131 | Improved |
| asynchronous updates for stable clique | Lazy Graph-LinUCB · Clique 9 (stiff, stable) | moves: 41 -> 11 | Improved |
| asynchronous updates for volatile clique | Lazy Graph-LinUCB · Clique 4 (volatile) | moves: 41 -> 15 | Improved |
| lazy updates for fairness threshold tuning | LinUCB · Adult Census fairness threshold | cumulative movement cost: 14.0 -> 2.5 | Improved |
| lazy updates for fairness threshold tuning | LinUCB · Adult Census fairness threshold | trajectory variance | Improved |
| lazy updates for fairness threshold tuning | LinUCB · Adult Census fairness threshold | convergence to tau=0.9 | No clear effect |
Closest papers by meaning
- Graph Reinforcement Learning for Network Control via Bi-Level Optimization (ICML 2023 · similarity 0.87)
- AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs (NeurIPS 2026 · similarity 0.86)
- Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity (NeurIPS 2026 · similarity 0.86)
- Efficient Graph Bandit Learning with Side-Observations and Switching Constraints (AAAI 2025 · similarity 0.85)
- Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces (ICML 2025 · similarity 0.85)
- Mode-conditioning unlocks superior test-time compute scaling (ICLR 2026 · similarity 0.84)
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.
