Research map / Learning theory and algorithms / Sample complexity
Experimental Designs for Heteroskedastic Variance
Justin David Naggar Weltz, Tanner Fiez, Alexander Volfovsky, Eric Laber, Blake Mason, houssam nassif, Lalit K Jain
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| HEAD adaptive-design variance estimator versus Separate Arm and Uniform estimators (ablation) | HEAD · synthetic arm sets X1 (200 unit-sphere arms) and X2 (1800 radius-0.1 arms), d=15 | mean absolute error of variance estimates | Improved |
| HEAD versus competing estimators across dimensions at fixed sample size 95k (ablation) | HEAD · synthetic arm sets, varying d | mean absolute error of variance estimates | Improved |
| estimate heteroskedastic variances (H-RAGE) instead of assuming homoskedastic noise (RAGE) (ablation) | H-RAGE · Example 1 signal-to-noise linear bandit, d=4, omega=0.02, q=0.4 | sample complexity | Improved |
| estimate heteroskedastic variances (H-RAGE) instead of RAGE (ablation) | H-RAGE · Example 2 benchmark with bent informative arms, d=3, alpha^2=1, beta^2=0.2 | sample complexity | Improved |
| account for heteroskedastic variances instead of upper bounding noise by sigma_max (ablation) | H-RAGE and heteroskedastic oracle · Experiment 3 multivariate testing, 2 variations in 3 dimensions | sample complexity | Improved |
| heteroskedastic oracle allocation versus homoskedastic oracle (ablation) | Oracle allocation · Experiment 3 multivariate testing | sampling weight allocation | Improved |
| increase kappa, the variance ratio, between heteroskedastic and homoskedastic algorithms | Optimal sample complexity comparison · theoretical comparison with kappa=20 | gap in optimal sample complexity | Mixed |
Closest papers by meaning
- Variance estimation in compound decision theory under boundedness (NeurIPS 2024 · similarity 0.84)
- Sub-Gaussian Confidence Intervals for Heavy-Tailed Data: Characterizing the Limits of Inference (NeurIPS 2026 · similarity 0.83)
- A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery (ICLR 2025 · similarity 0.83)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.83)
- Efficient Adaptive Experimentation with Noncompliance (NeurIPS 2025 · similarity 0.82)
- Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional Asymptotics (NeurIPS 2025 · similarity 0.82)
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.
