A one-bit quantized variant of Lloyd's algorithm for two-component sub-Gaussian mixtures achieves misclassification rates decaying exponentially with SNR comparable to unquantized data and exact recovery with separation only logarithmically worse than optimal.
Robust mean estimation under quantization.arXiv preprint arXiv:2601.07074, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
One-Bit Clustering for Two Component Sub-Gaussian Mixture Models
A one-bit quantized variant of Lloyd's algorithm for two-component sub-Gaussian mixtures achieves misclassification rates decaying exponentially with SNR comparable to unquantized data and exact recovery with separation only logarithmically worse than optimal.