Michael I. Jordan

TL;DR: The authors demonstrate that diverse representation in training data is key not only to increasing subgroup performances, but also to achieving population level objectives, and provide constructive results for using trends in existing data, alongside domain knowledge to help guide intentional, objective-aware dataset design.

TL;DR: In this paper, a Bayesian latent marked Poisson process is proposed for segmenting multiple objects in an image. But the model takes both shape and image feature/appearance into account, and it is not sufficient to utilize image information alone; incorporation of object shape prior models is necessary to obtain competitive segmentation performance.

TL;DR: This dissertation formalizes the phylogenomics methodology as a statistical graphical model of molecular function evolution, encapsulated in a framework called SIFTER (Statistical Inference of Function Through Evolutionary Relationships), which has performed well on a number of diverse protein families, as compared to standard annotation transfer methods and other phylogenomics-based approaches.

TL;DR: The reference book as discussed by the authors relates each myth to its culture and period of origin, and has detailed cross-referencing and indexing, and is intended to appeal to the serious student and general reader alike, whether they are seeking information on a particular mythological concept or on a culture, or on an individual character.

TL;DR: How second-order information can be used to speed up the dynamics of dual extrapolation methods despite inexactness is highlighted, and a simple and intuitive convergence analysis for second- order methods without requiring any compactness assumptions is provided.