Interpretability of ranking models is a crucial yet relatively under-examined research area. Recent progress on this area largely focuses on generating post-hoc explanations for existing black-box ranking models. Though promising, such post-hoc methods cannot provide sufficiently accurate explanations in general, which makes them infeasible in many high-stakes scenarios, especially the ones with legal or policy constraints. Thus, building an intrinsically interpretable ranking model with transparent, self-explainable structure becomes necessary, but this remains less explored in the learning-to-rank setting.

Breast cancer incidence and mortality rates vary geographically reflecting factors including regional and cultural differences in diet and lifestyle. There are numerous successful commercial mobile apps to help people control their diet and manage weight. However, such products are not suitable for people with special medical conditions that may require targeted dietary as well as motivational support. The paper presents a user centered approach of developing a Mobile Web App that focuses on breast cancer patients looking at their specific dietary, physical and mental requirements depending on the stage of their medical treatment. The paper explores the effect of incorporating gamification and social media as motivational drive to engage and motivate people to achieve their goals of adopting healthier eating habits while increasing physical activity in order ensure lasting lifestyle behavioural change. The design of PhytoCloud is being described, a gamified Mobile Web App that enables users to record their dietary habits and physical activity and motivate their consumption of food with oestrogen-like properties (phytoestrogens) which are linked to the prevention of reappearance of breast cancer. The paper concludes with a discussion of future directions and adaptations to the current design to suite a Mobile Native Application design.

Sparse matrix--matrix multiplication (SpGEMM) is a key operation in numerous areas from information to the physical sciences. Implementing SpGEMM efficiently on throughput-oriented processors, such as the graphics processing unit (GPU), requires the programmer to expose substantial fine-grained parallelism while conserving the limited off-chip memory bandwidth. Balancing these concerns, we decompose the SpGEMM operation into three highly parallel phases: expansion, sorting, and contraction, and introduce a set of complementary bandwidth-saving performance optimizations. Our implementation is fully general and our optimization strategy adaptively processes the SpGEMM workload row-wise to substantially improve performance by decreasing the work complexity and utilizing the memory hierarchy more effectively.

This article describes the algorithms, features, and implementation of PyDEC, a Python library for computations related to the discretization of exterior calculus. PyDEC facilitates inquiry into both physical problems on manifolds as well as purely topological problems on abstract complexes. We describe efficient algorithms for constructing the operators and objects that arise in discrete exterior calculus, lowest-order finite element exterior calculus, and in related topological problems. Our algorithms are formulated in terms of high-level matrix operations which extend to arbitrary dimension. As a result, our implementations map well to the facilities of numerical libraries such as NumPy and SciPy. The availability of such libraries makes Python suitable for prototyping numerical methods. We demonstrate how PyDEC is used to solve physical and topological problems through several concise examples.

Sparse matrix-vector multiplication (SpMV) is of singular importance in sparse linear algebra. In contrast to the uniform regularity of dense linear algebra, sparse operations encounter a broad spectrum of matrices ranging from the regular to the highly irregular. Harnessing the tremendous potential of throughput-oriented processors for sparse operations requires that we expose substantial fine-grained parallelism and impose sufficient regularity on execution paths and memory access patterns. We explore SpMV methods that are well-suited to throughput-oriented architectures like the GPU and which exploit several common sparsity classes. The techniques we propose are efficient, successfully utilizing large percentages of peak bandwidth. Furthermore, they deliver excellent total throughput, averaging 16 GFLOP/s and 10 GFLOP/s in double precision for structured grid and unstructured mesh matrices, respectively, on a GeForce GTX 285. This is roughly 2.8 times the throughput previously achieved on Cell BE and more than 10 times that of a quad-core Intel Clovertown system.

In this paper, we present a multigrid technique for efficiently deforming large surface and volume meshes. We show that a previous least-squares formulation for distortion minimization reduces to a Laplacian system on a general graph structure for which we derive an analytic expression. We then describe an efficient multigrid algorithm for solving the relevant equations. Here we develop novel prolongation and restriction operators used in the multigrid cycles. Combined with a simple but effective graph coarsening strategy, our algorithm can outperform other multigrid solvers and the factorization stage of direct solvers in both time and memory costs for large meshes. It is demonstrated that our solver can trade off accuracy for speed to achieve greater interactivity, which is attractive for manipulating large meshes. Our multigrid solver is particularly well suited for a mesh editing environment which does not permit extensive precomputation. Experimental evidence of these advantages is provided on a number of meshes with a wide range of size. With our mesh deformation solver, we also successfully demonstrate that visually appealing mesh animations can be generated from both motion capture data and a single base mesh even when they are inconsistent.