Robust Mean Estimation under Quantization
By: Pedro Abdalla, Junren Chen
Potential Business Impact:
Protects computer data from sneaky errors.
We consider the problem of mean estimation under quantization and adversarial corruption. We construct multivariate robust estimators that are optimal up to logarithmic factors in two different settings. The first is a one-bit setting, where each bit depends only on a single sample, and the second is a partial quantization setting, in which the estimator may use a small fraction of unquantized data.
Similar Papers
Robust Estimation Under Heterogeneous Corruption Rates
Machine Learning (CS)
Filters bad data to make computer learning better.
Enhancing Trustworthiness with Mixed Precision: Benchmarks, Opportunities, and Challenges
Machine Learning (CS)
Makes AI safer for important jobs.
Learning under Quantization for High-Dimensional Linear Regression
Machine Learning (Stat)
Makes computers learn faster with less data.