Machine learning offers a fantastically powerful toolkit for building useful complexprediction systems quickly. This paper argues it is dangerous to think ofthese quick wins as coming for free. Using the software engineering frameworkof technical debt, we find it is common to incur massive ongoing maintenancecosts in real-world ML systems. We explore several ML-specific risk factors toaccount for in system design. These include boundary erosion, entanglement,hidden feedback loops, undeclared consumers, data dependencies, configurationissues, changes in the external world, and a variety of system-level anti-patterns.

Predicting ad click-through rates (CTR) is a massive-scale learning problem that is central to the multi-billion dollar online advertising industry. We present a selection of case studies and topics drawn from recent experiments in the setting of a deployed CTR prediction system. These include improvements in the context of traditional supervised learning based on an FTRL-Proximal online learning algorithm (which has excellent sparsity and convergence properties) and the use of per-coordinate learning rates.

We present NetMesh, a new algorithm that produces a conforming Delaunay mesh for point sets in any fixed dimension with guaranteed optimal mesh size and quality. Our comparison-based algorithm runs in O(n log n + m) time, where n is the input size and m is the output size, and with constants depending only on the dimension and the desired element quality. It can terminate early in O(n log n) time returning a O(n) size Voronoi diagram of a superset of P, which again matches the known lower bounds.

Typical volume meshes in three dimensions are designed to conform to an underlying two-dimensional surface mesh, with volume mesh element size growing larger away from the surface. The surface mesh may be uniformly spaced or highly graded, and may have fine resolution due to extrinsic mesh size concerns. When we desire that such a volume mesh have good aspect ratio, we require that some space-filling scaffold vertices be inserted off the surface. We analyze the number of scaffold vertices in a setting that encompasses many existing volume meshing algorithms. We show that under simple preconditions, the number of scaffold vertices will be linear in the number of surface vertices.

The authors recently introduced the technique of sparse mesh refinement to produce the first near-optimal sequential time bounds of O(n lg L/s+m) for inputs in any fixed dimension with piecewiselinear constraining (PLC) features. This paper extends that work to the parallel case, refining the same inputs in time O(lg(L/s) lgm) on an EREW PRAM while maintaining the work bound; in practice, this means we expect linear speedup for any practical number of processors. This is faster than the best previously known parallel Delaunay mesh refinement algorithms in two dimensions. It is the first technique with work bounds equal to the sequential case. In higher dimension, it is the first provably fast parallel technique for any kind of quality mesh refinement with PLC inputs. Furthermore, the algorithm's implementation is straightforward enough that it is likely to be extremely fast in practice.

We present a new framework for maintaining the quality of two dimensional triangular moving meshes. The use of curved elements is the key idea that allows us to avoid excessive refinement and still obtain good quality meshes consisting of a low number of well shaped elements. We use B-splines curves to model object boundaries, and objects are meshed with second order Bézier triangles. As the mesh evolves according to a non-uniform flow velocity field, we keep track of object boundaries and, if needed, carefully modify the mesh to keep it well shaped by applying a combination of vertex insertion and deletion, edge flipping, and edge smoothing operations at each time step. Our algorithms for these tasks are extensions of known algorithms for meshes built of straight--sided elements and are designed for any fixed-order Bézier elements and B-splines. Although in this work we have concentrated on quadratic elements, most of the operations are valid for elements of any order and they generalize well to higher dimensions. We present results of our scheme for a set of objects mimicking red blood cells subject to a precomputed flow velocity field.