Research map / Learning theory and algorithms / Sample complexity
Robust Algorithms on Adaptive Inputs from Bounded Adversaries
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 private-median aggregation over independent randomized data structures | Adaptive query framework · Adaptive queries | space overhead: \Omega(Q) -> \tO{\sqrt{Q}} | Helped |
| Use the SRHT-specific construction and amortize privacy loss across independent per-point mechanisms | Adaptive distance estimation · Adaptive distance estimation | space: \wt{O}(n^{3 / 2} \sqrt{Q}) -> \wt{O} (n \sqrt{Q}) | Helped |
| Use the Lipschitz net construction to extend accuracy from a finite net to all queries | KDE data structure · Unlimited adaptive kernel density estimation | number of adaptive queries supported: any number | Helped |
| Use the proposed method instead of Baseline 1 | Adaptive norm estimation · Adaptive norm estimation | runtime | Helped |
| Use the proposed method instead of Baseline 1 | Adaptive norm estimation · Adaptive norm estimation | estimation variability | Hurt |
| Use Baseline 2 instead of Baseline 1 | Adaptive norm estimation · Adaptive norm estimation | estimation variability | Hurt |
Closest papers by meaning
- A Necessary and Sufficient Stability Notion for Adaptive Generalization (NeurIPS 2019 · similarity 0.87)
- Breaking the Quadratic Barrier: Robust Cardinality Sketches for Adaptive Queries (ICML 2025 · similarity 0.86)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.85)
- On the Learnability of Distribution Classes with Adaptive Adversaries (ICML 2025 · similarity 0.84)
- Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters (NeurIPS 2024 · similarity 0.84)
- Adaptive Data Analysis for Growing Data (NeurIPS 2025 · similarity 0.83)
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.