Machine Learning from Weak Supervision: An Empirical Risk Minimization Approach (Adaptive Computation and Machine Learning series)

The Weakly Supervised Learning Book is a comprehensive guide to mastering the fundamentals of machine learning from weakly labeled data.

With an emphasis on empirical risk minimization, this book provides both the basics and advanced mathematical theories underlying the field.

It covers various algorithms for supervised binary and multiclass classification, as well as problems of binary weakly supervised classification, including positive-unlabeled (PU) classification, positive-negative-unlabeled (PNU) classification, and unlabeled-unlabeled (UU) classification.

Additionally, it discusses complementary-label (CL) classification and partial-label (PL) classification in multiclass classification.

The book also addresses more advanced issues, including a family of correction methods to improve the generalization performance of weakly supervised learning and the problem of class-prior estimation.

Whether you're a practitioner or researcher, this book is an essential resource for anyone looking to master the art of weakly supervised learning.