NeurIPS 2020

Byzantine Resilient Distributed Multi-Task Learning

Meta Review

There was some disagreement in the initial reviews. Three reviewers were quite positive, noting that the intuitive algorithmic ideas, interesting results and good empirical evaluation. One reviewer was more negative, with some concerns regarding the scope of the approach (in particular due to the convex assumption) and the lack of discussion/evaluation on deep MTL models. After reading the author rebuttal and further discussion among reviewers, I consider that the restriction of the analysis to convex scenarios is acceptable given that this work appears to be the first one on Byzantine MTL and that the authors provide a basic experiment in the nonconvex setting. Therefore, the paper is accepted, but I ask the authors to add a detailed discussion of the nonconvex setting and encourage them to include more complete deep learning experiments in the final version.