Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis. (arXiv:2311.01052v1 [stat.ML])

We introduce Resilient Multiple Choice Learning (rMCL), an extension of the
MCL approach for conditional distribution estimation in regression settings
where multiple targets may be sampled for each training input. Multiple Choice
Learning is a simple framework to tackle multimodal density estimation, using
the Winner-Takes-All (WTA) loss for a set of hypotheses. In regression
settings, the existing MCL variants focus on merging the hypotheses, thereby
eventually sacrificing the diversity of the predictions. In contrast, our
method relies on a novel …

analysis application arxiv audio distribution extension framework multimodal multiple regression resilient scoring simple targets training