Research map / Learning theory and algorithms / Combinatorial and search optimization
Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| reformulate SPG-LS as a single SDP instead of bisection over many SDPs | SPG-LS · synthetic regression (m=2n, n=1000) | wall-clock time: 988.675 s to 45.984 s | Helped |
| reduce single SDP to SOCP via congruence transformations and generalized Schur complement (ablation) | single SDP reformulation · synthetic regression (m=2n, n=2000) | wall-clock time: 438.487 s to 0.536 s | Helped |
| reduce single SDP to SOCP (ablation) | single SDP reformulation · blog dataset | wall-clock time vs single SDP: SOCP takes about 1/50 the time of single SDP | Helped |
| SOCP reformulation vs bisection | SPG-LS · synthetic regression, up to (m,n)=(1000,2000) | speedup over bisection: up to 20,000+ times faster | Helped |
| single SDP reformulation vs bisection | SPG-LS · blog dataset | wall-clock time: single SDP takes about 1/20 the time of bisection | Helped |
| SOCP and single SDP achieve best average MSE vs bisection and ridge regression | SPG-LS · red wine and blog datasets (10-fold CV) | average MSE | No clear effect |
Closest papers by meaning
- Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares Reformulation (ICML 2022 · similarity 0.93)
- Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game (NeurIPS 2024 · similarity 0.89)
- Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents (NeurIPS 2023 · similarity 0.83)
- Safe Search for Stackelberg Equilibria in Extensive-Form Games (AAAI 2021 · similarity 0.83)
- Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis (NeurIPS 2025 · similarity 0.82)
- Transition-Informed Reinforcement Learning for Large-Scale Stackelberg Mean-Field Games (AAAI 2024 · similarity 0.80)
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.