2017 · 223 citations · 33 references
ComputingComputer ScienceMachine LearningStatistical LearningStatisticsBias-variance TradeoffOverfittingProbabilistic Machine LearningStatistical InferenceSupervised LearningUnsupervised Learning
The vast majority of theoretical results in machine learning and statistics assume that the training data is a reliable reflection of the phenomena to be learned. Similarly, most learning techniques used in practice are brittle to the presence of large amounts of biased or malicious data. Motivated by this, we consider two frameworks for studying estimation, learning, and optimization in the presence of significant fractions of arbitrary data.
33
Robust principal component analysis?
Emmanuel J. Candès, Xiaodong Li, Yi Ma et al. · Journal of the ACM · 2011 · 6.9K citations
Robust Statistics: The Approach Based on Influence Functions
David Ruppert, Frank R. Hampel, Elvezio Ronchetti et al. · Technometrics · 1987 · 3.8K citations
Rank-Sparsity Incoherence for Matrix Decomposition
SIAM Journal on Optimization · 2011 · 670 citations · Full text