Research map / Adversarial robustness and security / Certified and empirical robustness
Adversarial Robustness of Streaming Algorithms through Importance Sampling
Vladimir Braverman, Avinatan Hassidim, Yossi Matias, Mariano Schain, Sandeep Silwal, Samson Zhou
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 |
|---|---|---|---|
| Use online importance sampling instead of a fixed linear sketch | Streaming linear regression · Adversarial stream tailored to the sketching matrix | regression robustness | Improved |
| Use merge-and-reduce streaming k-means instead of Spark StreamingKMeans | Streaming k-means · Adversarial clustering stream with a distant final batch | per-sample loss | Improved |
| Use row sampling instead of River's streaming linear regression | Streaming linear regression · Adversarial stream with a distant final batch | regression loss | Improved |
| Use fresh independent randomness for each importance-sampling decision | Importance-sampling streaming algorithms · Adversarial streams | adversarial robustness | Improved |
| Apply merge and reduce to offline coreset constructions | Coreset-based streaming algorithms · Adversarial streams | coreset correctness | Improved |
Closest papers by meaning
- Improved Algorithms for White-Box Adversarial Streams (ICML 2023 · similarity 0.89)
- Adversarially Robust Streaming Algorithms via Differential Privacy (NeurIPS 2020 · similarity 0.89)
- Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters (NeurIPS 2024 · similarity 0.88)
- Clustering Effect of Adversarial Robust Models (NeurIPS 2021 · similarity 0.87)
- Fast White-Box Adversarial Streaming Without a Random Oracle (ICML 2024 · similarity 0.87)
- ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck (ICML 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.
