Research map / Learning theory and algorithms / Sample complexity
Approximate Supermodularity Bounds for Experimental Design
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 |
|---|---|---|---|
| Use greedy A-optimal design instead of random movie selection | EachMovie survey design · EachMovie | MAE: 2.8 and 3.3; greedy gives 2.3 at k=10 and < 1.8 for k ≥ 35 | Helped |
| Use greedy A-optimal design instead of random design | EachMovie genre prediction · EachMovie | genre misclassification rate: approximately 25% vs over 45% | Helped |
| Decrease experiment SNR | Greedy A- and E-optimal experimental design · A- and E-optimal design | greedy near-optimality guarantee: approaches 1-1/e | Helped |
| Use greedy A-optimal design at high SNR | Synthetic A-optimal design · High SNR | A-optimality value | No clear effect |
| Use greedy E-optimal design at low or high SNR | Synthetic E-optimal design · Low- and high-SNR simulations | E-optimality value | Helped |
Closest papers by meaning
- Design Amortization for Bayesian Optimal Experimental Design (AAAI 2023 · similarity 0.85)
- Corporate Needs You to Find the Difference: Revisiting Submodular and Supermodular Ratio Optimization Problems (NeurIPS 2025 · similarity 0.83)
- Near-Optimal Experiment Design in Linear non-Gaussian Cyclic Models (NeurIPS 2025 · similarity 0.82)
- Stronger Neyman Regret Guarantees for Adaptive Experimental Design (ICML 2025 · similarity 0.82)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.82)
- Online Two-Stage Submodular Maximization (NeurIPS 2025 · similarity 0.81)
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.