arXiv subjects

Benjamin W. Priest

Publications and source records attributed to Benjamin W. Priest.

21 records · Page 2Linked to original sources

arXiv2020

Quantum Machine Learning using Gaussian Processes with Performant Quantum Kernels

Quantum computers have the opportunity to be transformative for a variety of computational tasks. Recently, there have been proposals to use the unsimulatably of large quantum devices to perform regression, classification, and other machine learning tasks with quantum advantage by using kernel methods. While unsimulatably is a necessary condition for quantum advantage in machine learning, it is not sufficient, as not all kernels are equally effective. Here, we study the use of quantum computers to perform the machine learning tasks of one- and multi-dimensional regression, as well as reinforcement learning, using Gaussian Processes. By using approximations of performant classical kernels enhanced with extra quantum resources, we demonstrate that quantum devices, both in simulation and on hardware, can perform machine learning tasks at least as well as, and many times better than, the classical inspiration. Our informed kernel design demonstrates a path towards effectively utilizing quantum devices for machine learning tasks.

quant-ph↗

arXiv2020

Reinforcement Learning via Gaussian Processes with Neural Network Dual Kernels

While deep neural networks (DNNs) and Gaussian Processes (GPs) are both popularly utilized to solve problems in reinforcement learning, both approaches feature undesirable drawbacks for challenging problems. DNNs learn complex nonlinear embeddings, but do not naturally quantify uncertainty and are often data-inefficient to train. GPs infer posterior distributions over functions, but popular kernels exhibit limited expressivity on complex and high-dimensional data. Fortunately, recently discovered conjugate and neural tangent kernel functions encode the behavior of overparameterized neural networks in the kernel domain. We demonstrate that these kernels can be efficiently applied to regression and reinforcement learning problems by analyzing a baseline case study. We apply GPs with neural network dual kernels to solve reinforcement learning tasks for the first time. We demonstrate, using the well-understood mountain-car problem, that GPs empowered with dual kernels perform at least as well as those using the conventional radial basis function kernel. We conjecture that by inheriting the probabilistic rigor of GPs and the powerful embedding properties of DNNs, GPs using NN dual kernels will empower future reinforcement learning models on difficult domains.

cs.LG↗

arXiv2020

DegreeSketch: Distributed Cardinality Sketches on Massive Graphs with Applications

We present DegreeSketch, a semi-streaming distributed sketch data structure and demonstrate its utility for estimating local neighborhood sizes and local triangle count heavy hitters on massive graphs. DegreeSketch consists of vertex-centric cardinality sketches distributed across a set of processors that are accumulated in a single pass, and then behaves as a persistent query engine capable of approximately answering graph queries pertaining to the sizes of adjacency set unions and intersections. The $t$th local neighborhood of a vertex is the number of vertices reachable in $G$ from $v$ by traversing at most $t$ edges, whereas the local triangle count is the number of 3-cycles in which it is included. Both metrics are useful in graph analysis applications, but exact computations scale poorly as graph sizes grow. We present efficient algorithms for estimating both local neighborhood sizes and local triangle count heavy hitters using DegreeSketch. In our experiments we implement DegreeSketch using the celebrated hyperloglog cardinality sketch and utilize the distributed communication tool YGM to achieve state-of-the-art performance in distributed memory.

cs.DC↗