papers

Publications (40)

physics.ao-ph2020

Testing the Reliability of Interpretable Neural Networks in Geoscience Using the Madden-Julian Oscillation

Benjamin A. Toms, Karthik Kashinath, Prabhat +1

We test the reliability of two neural network interpretation techniques, backward optimization and layerwise relevance propagation, within geoscientific applications by applying th…

physics.ins-det2020

Track Seeding and Labelling with Embedded-space Graph Neural Networks

Nicholas Choma, Daniel Murnane, Xiangyang Ju +16

To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction. The most promisi…

astro-ph.IM2015

Celeste: Variational inference for a generative model of astronomical images

Jeffrey Regier, Andrew Miller, Jon McAuliffe +5

We present a new, fully generative model of optical telescope image sets, along with a variational procedure for inference. Each pixel intensity is treated as a Poisson random vari…

hep-ex2017

Deep Neural Networks for Physics Analysis on low-level whole-detector data at the LHC

Wahid Bhimji, Steven Andrew Farrell, Thorsten Kurth +3

There has been considerable recent activity applying deep convolutional neural nets (CNNs) to data from particle physics experiments. Current approaches on ATLAS/CMS have largely f…

cs.LG2021

Learning from learning machines: a new generation of AI technology to meet the needs of science

Luca Pion-Tonachini, Kristofer Bouchard, Hector Garcia Martin +33

We outline emerging opportunities and challenges to enhance the utility of AI for scientific discovery. The distinct goals of AI for industry versus the goals of AI for science cre…

physics.comp-ph2019

DisCo: Physics-Based Unsupervised Discovery of Coherent Structures in Spatiotemporal Systems

Adam Rupe, Nalini Kumar, Vladislav Epifanov +8

Extracting actionable insight from complex unlabeled scientific data is an open challenge and key to unlocking data-driven discovery in science. Complementary and alternative to su…

cs.LG2018

Graph Neural Networks for IceCube Signal Classification

Nicholas Choma, Federico Monti, Lisa Gerhardt +7

Tasks involving the analysis of geometric (graph- and manifold-structured) data have recently gained prominence in the machine learning community, giving birth to a rapidly develop…

cs.LG2020

MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework

Chiyu Max Jiang, Soheil Esmaeilzadeh, Kamyar Azizzadenesheli +6

We propose MeshfreeFlowNet, a novel deep learning-based super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the low-resolution inputs. Whil…

stat.ML2015

Scalable Bayesian Optimization Using Deep Neural Networks

Jasper Snoek, Oren Rippel, Kevin Swersky +6

Bayesian optimization is an effective methodology for the global optimization of functions with expensive evaluations. It relies on querying a distribution over functions defined b…

cs.DC2016

PANDA: Extreme Scale Parallel K-Nearest Neighbor on Distributed Architectures

Md. Mostofa Ali Patwary, Nadathur Rajagopalan Satish, Narayanan Sundaram +8

Computing -Nearest Neighbors (KNN) is one of the core kernels used in many machine learning, data mining and scientific computing applications. Although kd-tree based $O(\log n)…

cs.PF2017

Deep Learning at 15PF: Supervised and Semi-Supervised Classification for Scientific Data

Thorsten Kurth, Jian Zhang, Nadathur Satish +12

This paper presents the first, 15-PetaFLOP Deep Learning system for solving scientific pattern classification problems on contemporary HPC architectures. We develop supervised conv…

cs.LG2019

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale

Atılım Güneş Baydin, Lei Shao, Wahid Bhimji +14

Probabilistic programming languages (PPLs) are receiving widespread attention for performing Bayesian inference in complex generative models. However, applications to science remai…

astro-ph.CO2018

CosmoFlow: Using Deep Learning to Learn the Universe at Scale

Amrita Mathuriya, Deborah Bard, Peter Mendygral +14

Deep learning is a promising tool to determine the physical model that describes our universe. To handle the considerable computational cost of this problem, we present CosmoFlow:…

stat.AP2019

Approximate Inference for Constructing Astronomical Catalogs from Images

Jeffrey Regier, Andrew C. Miller, David Schlegel +3

We present a new, fully generative model for constructing astronomical catalogs from optical telescope image sets. Each pixel intensity is treated as a random variable with paramet…

cs.DB2017

ArrayBridge: Interweaving declarative array processing with high-performance computing

Haoyuan Xing, Sofoklis Floratos, Spyros Blanas +4

Scientists are increasingly turning to datacenter-scale computers to produce and analyze massive arrays. Despite decades of database research that extols the virtues of declarative…

cs.CV2019

Spherical CNNs on Unstructured Grids

Chiyu "Max" Jiang, Jingwei Huang, Karthik Kashinath +3

We present an efficient convolution kernel for Convolutional Neural Networks (CNNs) on unstructured grids using parameterized differential operators while focusing on spherical sig…

cs.DC2018

Accelerating Large-Scale Data Analysis by Offloading to High-Performance Computing Libraries using Alchemist

Alex Gittens, Kai Rothauge, Shusen Wang +6

Apache Spark is a popular system aimed at the analysis of large data sets, but recent studies have shown that certain computations---in particular, many linear algebra computations…

stat.ML2017

Union of Intersections (UoI) for Interpretable Data Driven Discovery and Prediction

Kristofer E. Bouchard, Alejandro F. Bujan, Farbod Roosta-Khorasani +7

The increasing size and complexity of scientific data could dramatically enhance discovery and prediction for basic scientific applications. Realizing this potential, however, requ…

cs.CV2017

ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events

Evan Racah, Christopher Beckham, Tegan Maharaj +3

Then detection and identification of extreme weather events in large-scale climate simulations is an important problem for risk management, informing governmental policy decisions…

stat.ML2016

Revealing Fundamental Physics from the Daya Bay Neutrino Experiment using Deep Neural Networks

Evan Racah, Seyoon Ko, Peter Sadowski +5

Experiments in particle physics produce enormous quantities of data that must be analyzed and interpreted by teams of physicists. This analysis is often exploratory, where scientis…

physics.ins-det2020

Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors

Xiangyang Ju, Steven Farrell, Paolo Calafiura +20

Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and…

cs.DC2017

An Assessment of Data Transfer Performance for Large-Scale Climate Data Analysis and Recommendations for the Data Infrastructure for CMIP6

Eli Dart, Michael F. Wehner, Prabhat

We document the data transfer workflow, data transfer performance, and other aspects of staging approximately 56 terabytes of climate model output data from the distributed Coupled…

cs.DC2016

Learning an Astronomical Catalog of the Visible Universe through Scalable Bayesian Inference

Jeffrey Regier, Kiran Pamnany, Ryan Giordano +4

Celeste is a procedure for inferring astronomical catalogs that attains state-of-the-art scientific results. To date, Celeste has been scaled to at most hundreds of megabytes of as…

physics.comp-ph2019

Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems

Jin-Long Wu, Karthik Kashinath, Adrian Albert +3

Simulating complex physical systems often involves solving partial differential equations (PDEs) with some closures due to the presence of multi-scale physics that cannot be fully…

cs.DC2018

Alchemist: An Apache Spark <=> MPI Interface

Alex Gittens, Kai Rothauge, Shusen Wang +6

The Apache Spark framework for distributed computation is popular in the data analytics community due to its ease of use, but its MapReduce-style programming model can incur signif…

cs.LG2020

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model

Atılım Güneş Baydin, Lukas Heinrich, Wahid Bhimji +12

We present a novel probabilistic programming framework that couples directly to existing large-scale simulators through a cross-platform probabilistic execution protocol, which all…

hep-ex2018

Novel deep learning methods for track reconstruction

Steven Farrell, Paolo Calafiura, Mayur Mudigonda +11

For the past year, the HEP.TrkX project has been investigating machine learning solutions to LHC particle track reconstruction problems. A variety of models were studied that drew…

cs.DC2018

Cataloging the Visible Universe through Bayesian Inference at Petascale

Jeffrey Regier, Kiran Pamnany, Keno Fischer +9

Astronomical catalogs derived from wide-field imaging surveys are an important tool for understanding the Universe. We construct an astronomical catalog from 55 TB of imaging data…

cs.DC2017

Scaling GRPC Tensorflow on 512 nodes of Cori Supercomputer

Amrita Mathuriya, Thorsten Kurth, Vivek Rane +5

We explore scaling of the standard distributed Tensorflow with GRPC primitives on up to 512 Intel Xeon Phi (KNL) nodes of Cori supercomputer with synchronous stochastic gradient de…

cs.DC2018

Exascale Deep Learning for Climate Analytics

Thorsten Kurth, Sean Treichler, Joshua Romero +9

We extract pixel-level masks of extreme weather patterns using variants of Tiramisu and DeepLabv3+ neural networks. We describe improvements to the software frameworks, input pipel…

physics.comp-ph2019

Highly-scalable, physics-informed GANs for learning solutions of stochastic PDEs

Liu Yang, Sean Treichler, Thorsten Kurth +8

Uncertainty quantification for forward and inverse problems is a central challenge across physical and biomedical disciplines. We address this challenge for the problem of modeling…

cs.AI2017

Improvements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators

Mario Lezcano Casado, Atilim Gunes Baydin, David Martinez Rubio +8

We consider the problem of Bayesian inference in the family of probabilistic models implicitly defined by stochastic generative models of data. In scientific fields ranging from po…

cs.CV2016

Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets

Yunjie Liu, Evan Racah, Prabhat +6

Detecting extreme events in large datasets is a major challenge in climate science research. Current algorithms for extreme event detection are build upon human expertise in defini…

cs.DC2016

Matrix Factorization at Scale: a Comparison of Scientific Data Analytics in Spark and C+MPI Using Three Case Studies

Alex Gittens, Aditya Devarakonda, Evan Racah +14

We explore the trade-offs of performing linear algebra using Apache Spark, compared to traditional C and MPI implementations on HPC platforms. Spark is designed for data analytics…

physics.comp-ph2019

Towards Unsupervised Segmentation of Extreme Weather Events

Adam Rupe, Karthik Kashinath, Nalini Kumar +3

Extreme weather is one of the main mechanisms through which climate change will directly impact human society. Coping with such change as a global community requires markedly impro…

astro-ph.CO2017

Galactos: Computing the Anisotropic 3-Point Correlation Function for 2 Billion Galaxies

Brian Friesen, Md. Mostofa Ali Patwary, Brian Austin +8

The nature of dark energy and the complete theory of gravity are two central questions currently facing cosmology. A vital tool for addressing them is the 3-point correlation funct…

cs.LG2018

Optimizing the Union of Intersections LASSO () and Vector Autoregressive () Algorithms for Improved Statistical Estimation at Scale

Mahesh Balasubramanian, Trevor Ruiz, Brandon Cook +4

The analysis of scientific data of increasing size and complexity requires statistical machine learning methods that are both interpretable and predictive. Union of Intersections (…

stat.CO2013

Parallelizing Gaussian Process Calculations in R

Christopher J. Paciorek, Benjamin Lipshitz, Wei Zhuo +3

We consider parallel computation for Gaussian process calculations to overcome computational and memory constraints on the size of datasets that can be analyzed. Using a hybrid par…

physics.flu-dyn2017

A Physics-Based Approach to Unsupervised Discovery of Coherent Structures in Spatiotemporal Systems

A. Rupe, J. P. Crutchfield, K. Kashinath +1

Given that observational and numerical climate data are being produced at ever more prodigious rates, increasingly sophisticated and automated analysis techniques have become essen…

quant-ph2021

Simulation of Lennard-Jones Potential on a Quantum Computer

Prabhat, Bikash K. Behera

Simulation of time dynamical physical problems has been a challenge for classical computers due to their time-complexity. To demonstrate the dominance of quantum computers over cla…