Researchers have developed a new polynomial-time algorithm for estimating linear regressors with self-selection bias. This algorithm improves upon previous methods by removing the exponential dependence on the number of regressors (k) in the running time. The new approach also handles correlated noise between regressors, leading to the first polynomial-time solution for the max-affine regression problem. The method relies on an improved understanding of covariate moments and tensor decomposition techniques. AI
RANK_REASON The item describes a new algorithm and theoretical results published in a research paper. [lever_c_demoted from research: ic=1 ai=0.4]
Read on Hugging Face Daily Papers →
- ACM Symposium on Theory of Computing
- CDIZ23
- Cherapanamjeri
- computational learning theory
- Daskalakis
- Gaitonde
- Ghosh
- GPGR22
- Guntuboyina
- IEEE Transactions on Information Theory
- Ilyas
- Kalavasis
- KMZ26
- Mehrotra
- Mossel
- Pananjady
- Ramchandran
- Zampetakis
- zhou
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →