Benchmarking Machine-Learning Software and Hardware for Quantitative Economics

TL;DR: In this paper , the authors found that the impact of the E-Government Development Index (EGDI) on WGI was the greatest in the indicators of government effectiveness and regulatory quality, with a score above 0.53.

TL;DR: In this paper, an overview of the implementation of ML in discovery of new materials and characterization of materials ML is given, as well as how ML is applied to model materials and how ML models for materials manufacturing are discussed.

TL;DR: This paper shows how to use FPGAs and their associated high-level synthesis compilers to solve heterogeneous agent models with incomplete markets and aggregate uncertainty, and document that the acceleration delivered by one single FPGA is comparable to that provided by using 74 CPU cores in a conventional cluster.

TL;DR: Researchers develop a machine learning algorithm for solving high-dimensional continuous-time finance models, leveraging deep learning and automatic differentiation to compute exact expectations with negligible computational cost, enabling new economic insights in asset pricing, corporate finance, and portfolio choice.

TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.

TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

TL;DR: GNMT, Google's Neural Machine Translation system, is presented, which attempts to address many of the weaknesses of conventional phrase-based translation systems and provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delicited models.

TL;DR: In this paper, a new approach for approximating the value of American options by simulation is presented, using least squares to estimate the conditional expected payoff to the optionholder from continuation.