Brief

Researchers have developed a new method for online inverse linear optimization, a technique used in contextual recommendation systems. This approach achieves a finite regret bound of O(d log d) for M-convex action sets, a significant improvement over previous exponential bounds and a partial answer to an open question in the field. The method combines structural characterization of optimal solutions with geometric volume arguments. Additionally, the technique has been extended to handle adversarially corrupted feedback, yielding a bound of O((C+1)d log d) without prior knowledge of the corruption level. AI

Researchers have developed a new method for online learning in a random-order model, where data is revealed sequentially and in a shuffled manner. This approach extends existing batch-to-online transformations to achieve small-loss regret bounds, which are typically better than previous approximate regret guarantees. The technique is applicable to various problems, including online k-means clustering, low-rank approximation, and submodular function minimization, highlighting the effectiveness of sparsification methods. AI