Learning with rejection
Abstract
We introduce a novel framework for classification with a rejection
option that consists of simultaneously learning two functions:
a classifier along with a rejection function. We present a full theoretical
analysis of this framework including new data-dependent learning
bounds in terms of the Rademacher complexities of the classifier and
rejection families as well as consistency and calibration results. These
theoretical guarantees guide us in designing new algorithms that can
exploit different kernel-based hypothesis sets for the classifier and rejection
functions. We compare and contrast our general framework with the
special case of confidence-based rejection for which we devise alternative
loss functions and algorithms as well. We report the results of several experiments
showing that our kernel-based algorithms can yield a notable
improvement over the best existing confidence-based rejection algorithm.
option that consists of simultaneously learning two functions:
a classifier along with a rejection function. We present a full theoretical
analysis of this framework including new data-dependent learning
bounds in terms of the Rademacher complexities of the classifier and
rejection families as well as consistency and calibration results. These
theoretical guarantees guide us in designing new algorithms that can
exploit different kernel-based hypothesis sets for the classifier and rejection
functions. We compare and contrast our general framework with the
special case of confidence-based rejection for which we devise alternative
loss functions and algorithms as well. We report the results of several experiments
showing that our kernel-based algorithms can yield a notable
improvement over the best existing confidence-based rejection algorithm.
Research Areas
