PulseAugur
EN
LIVE 12:46:52

New AC-IHT algorithm tackles data contamination in high-dimensional regression

Researchers have developed a new algorithm called Adversarial Contamination-resistant Iterative Hard Thresholding (AC-IHT) designed to handle high-dimensional regression problems affected by data contamination. This two-stage, nonconvex algorithm iteratively refines coefficient and contamination vectors to achieve near-optimal estimation. The AC-IHT algorithm is also signal-adaptive, capable of attaining sharper estimation rates and more accurate support recovery under specific signal conditions, while providing a theoretical foundation for asymptotic inference. AI

IMPACT Introduces a novel algorithm for robust statistical analysis in machine learning, potentially improving model reliability in the presence of noisy data.

RANK_REASON The cluster contains a research paper detailing a new algorithm for statistical machine learning.

Read on arXiv stat.ML →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New AC-IHT algorithm tackles data contamination in high-dimensional regression

COVERAGE [2]

  1. arXiv stat.ML TIER_1 English(EN) · Shixiang Liu, Hanming Yang ·

    Adversarial Contamination Meets Hard Thresholding: An Iterative Algorithm with Signal Adaptivity and Minimax Optimality

    arXiv:2606.27685v1 Announce Type: new Abstract: Pervasive data contamination -- stemming from measurement errors, outliers, or adversarial corruption -- has motivated the development of robust statistical methods. In this context, we propose a two-stage Adversarial Contamination-…

  2. arXiv stat.ML TIER_1 English(EN) · Hanming Yang ·

    Adversarial Contamination Meets Hard Thresholding: An Iterative Algorithm with Signal Adaptivity and Minimax Optimality

    Pervasive data contamination -- stemming from measurement errors, outliers, or adversarial corruption -- has motivated the development of robust statistical methods. In this context, we propose a two-stage Adversarial Contamination-resistant Iterative Hard Thresholding (AC-IHT) a…