Research map / Label-efficient and robust learning / OOD and anomaly detection
Heterogeneous Risk Minimization
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 |
|---|---|---|---|
| Jointly identify latent heterogeneous environments and learn an invariant predictor with HRM | Pooled training data in selection-bias simulations · Selection bias simulation, r=1.5, r=1.9, and r=2.3 | Mean_Error: 0.460 -> 0.447; 0.456 -> 0.449; 0.461 -> 0.447 | Helped |
| Jointly identify latent heterogeneous environments and learn an invariant predictor with HRM | Pooled training data in selection-bias simulations · Selection bias simulation, d=10, d=20, and d=40 | Mean_Error: 0.456 -> 0.449; 0.484 -> 0.466; 0.500 -> 0.465 | Helped |
| Jointly identify latent heterogeneous environments and learn an invariant predictor with HRM | Pooled training data in anti-causal effect simulations · Anti-causal effect, test e10 in both dimensional settings | Prediction error: 0.392 -> 0.320; 0.504 -> 0.335 | Helped |
| Add the iterative feedback loop between heterogeneity identification and invariant learning (ablation) | HRM · Selection bias simulation, r=1.9 | Mean_Error: 0.488 -> 0.449 | Helped |
| Add the iterative feedback loop between heterogeneity identification and invariant learning (ablation) | HRM · Anti-causal effect, nφ=9, nψ=1, test e10 | Prediction error: 1.430 -> 0.320 | Helped |
| Add the iterative feedback loop between heterogeneity identification and invariant learning (ablation) | HRM · Anti-causal effect, nφ=5, nψ=5, test e10 | Prediction error: 0.533 -> 0.335 | Helped |
Closest papers by meaning
- Integrated Latent Heterogeneity and Invariance Learning in Kernel Space (NeurIPS 2021 · similarity 0.91)
- Empirical or Invariant Risk Minimization? A Sample Complexity Perspective (ICLR 2021 · similarity 0.90)
- Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization (ICLR 2023 · similarity 0.89)
- Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization (ICLR 2025 · similarity 0.87)
- Invariant Risk Minimization Is A Total Variation Model (ICML 2024 · similarity 0.85)
- Sufficient Invariant Learning for Distribution Shift (CVPR 2025 · similarity 0.85)
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.