John Wright’s research while affiliated with The Graduate Center, CUNY and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (124)


Detecting and diagnosing terrestrial gravitational-wave mimics through feature learning
  • Article

March 2023

·

9 Reads

·

2 Citations

Physical Review D

Robert E. Colgan

·

Zsuzsa Márka

·

Jingkai Yan

·

[...]

·

Szabolcs Márka

As engineered systems grow in complexity, there is an increasing need for automatic methods that can detect, diagnose, and even correct transient anomalies that inevitably arise and can be difficult or impossible to diagnose and fix manually. Among the most sensitive and complex systems of our civilization are the detectors that search for incredibly small variations in distance caused by gravitational waves—phenomena originally predicted by Albert Einstein to emerge and propagate through the universe as the result of collisions between black holes and other massive objects in deep space. The extreme complexity and precision of such detectors causes them to be subject to transient noise issues that can significantly limit their sensitivity and effectiveness. They are also subject to nearly constant development, improvement, commissioning and other invasive actions that change the nature of the data and its artifact contamination. In this work, we present a demonstration of a method that can detect and characterize emergent transient anomalies of such massively complex systems. We illustrate the performance, precision, and adaptability of the automated solution via one of the prevalent issues limiting gravitational-wave discoveries: noise artifacts of terrestrial origin that contaminate gravitational wave observatories’ highly sensitive measurements and can obscure or even mimic the faint astrophysical signals for which they are listening. Specifically, we demonstrate how a highly interpretable convolutional classifier can automatically learn to detect transient anomalies from auxiliary detector data without needing to observe the anomalies themselves. We also illustrate several other useful features of the model, including how it performs automatic variable selection to reduce tens of thousands of auxiliary data channels to only a few relevant ones; how it identifies behavioral signatures predictive of anomalies in those channels; and how it can be used to investigate individual anomalies and the channels associated with them. The solution outlined is broadly applicable, enabling automated anomaly discovery and characterization and human-in-the-loop anomaly elimination.


Figure 1. PCP-NMF loadings for chemical constituents of PM 2.5 . Constituents are listed using chemical formulas or abbreviations.
Summary Statistics for Daily Number of ED Visits for Myocardial Infarction in NYC (2007-2015), Total PM 2.5 , PM 2.5 Constituents, Daily Ambient Temperature and Relative Humidity
Applying principal component pursuit to investigate the association between source-specific fine particulate matter and myocardial infarction hospitalizations in New York City
  • Article
  • Full-text available

February 2023

·

16 Reads

·

4 Citations

Environmental Epidemiology

Unlabelled: The association between fine particulate matter (PM2.5) and cardiovascular outcomes is well established. To evaluate whether source-specific PM2.5 is differentially associated with cardiovascular disease in New York City (NYC), we identified PM2.5 sources and examined the association between source-specific PM2.5 exposure and risk of hospitalization for myocardial infarction (MI). Methods: We adapted principal component pursuit (PCP), a dimensionality-reduction technique previously used in computer vision, as a novel pattern recognition method for environmental mixtures to apportion speciated PM2.5 to its sources. We used data from the NY Department of Health Statewide Planning and Research Cooperative System of daily city-wide counts of MI admissions (2007-2015). We examined associations between same-day, lag 1, and lag 2 source-specific PM2.5 exposure and MI admissions in a time-series analysis, using a quasi-Poisson regression model adjusting for potential confounders. Results: We identified four sources of PM2.5 pollution: crustal, salt, traffic, and regional and detected three single-species factors: cadmium, chromium, and barium. In adjusted models, we observed a 0.40% (95% confidence interval [CI]: -0.21, 1.01%) increase in MI admission rates per 1 μg/m3 increase in traffic PM2.5, a 0.44% (95% CI: -0.04, 0.93%) increase per 1 μg/m3 increase in crustal PM2.5, and a 1.34% (95% CI: -0.46, 3.17%) increase per 1 μg/m3 increase in chromium-related PM2.5, on average. Conclusions: In our NYC study, we identified traffic, crustal dust, and chromium PM2.5 as potentially relevant sources for cardiovascular disease. We also demonstrated the potential utility of PCP as a pattern recognition method for environmental mixtures.

Download

Architectural optimization and feature learning for high-dimensional time series datasets

January 2023

·

5 Reads

·

2 Citations

Physical Review D

As our ability to sense increases, we are experiencing a transition from data-poor problems, in which the central issue is a lack of relevant data, to data-rich problems, in which the central issue is to identify a few relevant features in a sea of observations. Motivated by applications in gravitational-wave astrophysics, we study a problem in which the goal is to predict the presence of transient noise artifacts in a gravitational-wave detector from a rich collection of measurements from the detector and its environment. We argue that feature learning—in which relevant features are optimized from data—is critical to achieving high accuracy. We introduce models that reduce the error rate by over 60% compared to the previous state of the art, which used fixed, hand-crafted features. Feature learning is useful not only because it can improve performance on prediction tasks; the results provide valuable information about patterns associated with phenomena of interest that would otherwise be impossible to discover. In our motivating application, features found to be associated with transient noise provide diagnostic information about its origin and suggest mitigation strategies. Learning in such a high-dimensional setting is challenging. Through experiments with a variety of architectures, we identify two key factors in high-performing models: sparsity, for selecting relevant variables within the high-dimensional observations, and depth, which confers flexibility for handling complex interactions and robustness with respect to temporal variations. We illustrate their significance through a systematic series of experiments on real gravitational-wave detector data. Our results provide experimental corroboration of common assumptions in the machine-learning community and have direct applicability to improving our ability to sense gravitational waves, as well as to a wide variety of problem settings with similarly high-dimensional, noisy, or partly irrelevant data.


Principal Component Pursuit for Pattern Identification in Environmental Mixtures

November 2022

·

23 Reads

·

16 Citations

Environmental Health Perspectives

Background: Environmental health researchers often aim to identify sources or behaviors that give rise to potentially harmful environmental exposures. Objective: We adapted principal component pursuit (PCP)-a robust and well-established technique for dimensionality reduction in computer vision and signal processing-to identify patterns in environmental mixtures. PCP decomposes the exposure mixture into a low-rank matrix containing consistent patterns of exposure across pollutants and a sparse matrix isolating unique or extreme exposure events. Methods: We adapted PCP to accommodate nonnegative data, missing data, and values below a given limit of detection (LOD). We simulated data to represent environmental mixtures of two sizes with increasing proportions <LOD and three noise structures. We applied PCP-LOD to evaluate its performance in comparison with principal component analysis (PCA). We next applied principal component pursuit with limit of detection (PCP-LOD) to an exposure mixture of 21 persistent organic pollutants (POPs) measured in 1,000 U.S. adults from the 2001-2002 National Health and Nutrition Examination Survey (NHANES). We applied singular value decomposition to the estimated low-rank matrix to characterize the patterns. Results: PCP-LOD recovered the true number of patterns through cross-validation for all simulations; based on an a priori specified criterion, PCA recovered the true number of patterns in 32% of simulations. PCP-LOD achieved lower relative predictive error than PCA for all simulated data sets with up to 50% of the data <LOD. When 75% of values were <LOD, PCP-LOD outperformed PCA only when noise was low. In the POP mixture, PCP-LOD identified a rank-three underlying structure and separated 6% of values as extreme events. One pattern represented comprehensive exposure to all POPs. The other patterns grouped chemicals based on known structure and toxicity. Discussion: PCP-LOD serves as a useful tool to express multidimensional exposures as consistent patterns that, if found to be related to adverse health, are amenable to targeted public health messaging. https://doi.org/10.1289/EHP10479.



Boosting the efficiency of parametric detection with hierarchical neural networks

September 2022

·

7 Reads

·

3 Citations

Physical Review D

Gravitational-wave astronomy is a vibrant field that leverages both classic and modern data processing techniques for the understanding of the Universe. Various approaches have been proposed for improving the efficiency of the detection scheme, with hierarchical matched filtering being an important strategy. Meanwhile, deep learning methods have recently demonstrated both consistency with matched filtering methods and remarkable statistical performance. In this work, we propose a hierarchical detection network (HDN), a novel approach to efficient detection that combines ideas from hierarchical matching and deep learning. The network is trained using a novel loss function, which encodes simultaneously the goals of statistical accuracy and efficiency. We discuss the source of complexity reduction of the proposed model and describe a general recipe for initialization with each layer specializing in different regions. We demonstrate the performance of the HDN with experiments using open LIGO data and synthetic injections, and observe with two-layer models a 79% efficiency gain compared with matched filtering at an equal error rate of 0.2%. Furthermore, we show how training a three-layer HDN initialized using a two-layer model can further boost both accuracy and efficiency, highlighting the power of multiple simple layers in efficient detection.


Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks

July 2022

·

5 Reads

Gravitational wave astronomy is a vibrant field that leverages both classic and modern data processing techniques for the understanding of the universe. Various approaches have been proposed for improving the efficiency of the detection scheme, with hierarchical matched filtering being an important strategy. Meanwhile, deep learning methods have recently demonstrated both consistency with matched filtering methods and remarkable statistical performance. In this work, we propose Hierarchical Detection Network (HDN), a novel approach to efficient detection that combines ideas from hierarchical matching and deep learning. The network is trained using a novel loss function, which encodes simultaneously the goals of statistical accuracy and efficiency. We discuss the source of complexity reduction of the proposed model, and describe a general recipe for initialization with each layer specializing in different regions. We demonstrate the performance of HDN with experiments using open LIGO data and synthetic injections, and observe with two-layer models a 79%79\% efficiency gain compared with matched filtering at an equal error rate of 0.2%0.2\%. Furthermore, we show how training a three-layer HDN initialized using two-layer model can further boost both accuracy and efficiency, highlighting the power of multiple simple layers in efficient detection.


Detecting and Diagnosing Terrestrial Gravitational-Wave Mimics Through Feature Learning

March 2022

·

5 Reads

As engineered systems grow in complexity, there is an increasing need for automatic methods that can detect, diagnose, and even correct transient anomalies that inevitably arise and can be difficult or impossible to diagnose and fix manually. Among the most sensitive and complex systems of our civilization are the detectors that search for incredibly small variations in distance caused by gravitational waves -- phenomena originally predicted by Albert Einstein to emerge and propagate through the universe as the result of collisions between black holes and other massive objects in deep space. The extreme complexity and precision of such detectors causes them to be subject to transient noise issues that can significantly limit their sensitivity and effectiveness. In this work, we present a demonstration of a method that can detect and characterize emergent transient anomalies of such massively complex systems. We illustrate the performance, precision, and adaptability of the automated solution via one of the prevalent issues limiting gravitational-wave discoveries: noise artifacts of terrestrial origin that contaminate gravitational wave observatories' highly sensitive measurements and can obscure or even mimic the faint astrophysical signals for which they are listening. Specifically, we demonstrate how a highly interpretable convolutional classifier can automatically learn to detect transient anomalies from auxiliary detector data without needing to observe the anomalies themselves. We also illustrate several other useful features of the model, including how it performs automatic variable selection to reduce tens of thousands of auxiliary data channels to only a few relevant ones; how it identifies behavioral signatures predictive of anomalies in those channels; and how it can be used to investigate individual anomalies and the channels associated with them.


Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization

March 2022

·

25 Reads

Achieving invariance to nuisance transformations is a fundamental challenge in the construction of robust and reliable vision systems. Existing approaches to invariance scale exponentially with the dimension of the family of transformations, making them unable to cope with natural variabilities in visual data such as changes in pose and perspective. We identify a common limitation of these approaches--they rely on sampling to traverse the high-dimensional space of transformations--and propose a new computational primitive for building invariant networks based instead on optimization, which in many scenarios provides a provably more efficient method for high-dimensional exploration than sampling. We provide empirical and theoretical corroboration of the efficiency gains and soundness of our proposed method, and demonstrate its utility in constructing an efficient invariant network for a simple hierarchical object detection task when combined with unrolled optimization. Code for our networks and experiments is available at https://github.com/sdbuch/refine.


Architectural Optimization and Feature Learning for High-Dimensional Time Series Datasets

February 2022

·

13 Reads

As our ability to sense increases, we are experiencing a transition from data-poor problems, in which the central issue is a lack of relevant data, to data-rich problems, in which the central issue is to identify a few relevant features in a sea of observations. Motivated by applications in gravitational-wave astrophysics, we study the problem of predicting the presence of transient noise artifacts in a gravitational wave detector from a rich collection of measurements from the detector and its environment. We argue that feature learning--in which relevant features are optimized from data--is critical to achieving high accuracy. We introduce models that reduce the error rate by over 60\% compared to the previous state of the art, which used fixed, hand-crafted features. Feature learning is useful not only because it improves performance on prediction tasks; the results provide valuable information about patterns associated with phenomena of interest that would otherwise be undiscoverable. In our application, features found to be associated with transient noise provide diagnostic information about its origin and suggest mitigation strategies. Learning in high-dimensional settings is challenging. Through experiments with a variety of architectures, we identify two key factors in successful models: sparsity, for selecting relevant variables within the high-dimensional observations; and depth, which confers flexibility for handling complex interactions and robustness with respect to temporal variations. We illustrate their significance through systematic experiments on real detector data. Our results provide experimental corroboration of common assumptions in the machine-learning community and have direct applicability to improving our ability to sense gravitational waves, as well as to many other problem settings with similarly high-dimensional, noisy, or partly irrelevant data.


Citations (62)


... Gravity Spy data products, including both ML and volunteer classifications of the entire set of glitches up through O3, are available for public use [39,40], with proprietary data from ongoing observing runs similarly available to LVK scientists. Gravity Spy classifications have been used to examine how different glitch classes affect data analysis [41][42][43][44], for example, how they may contaminate GW searches [45]; the development of algorithms to distinguish GW signals from glitches [46][47][48][49][50][51][52][53][54][55][56][57][58][59][60][61][62][63]; the development of techniques to remove glitches from the data [64][65][66]; investigations of potential environmental or instrumental origins of noise [12,[67][68][69], such as what triggers the appearance of lightscattering noise [19,33]; simulating synthetic (noisy) GW data [70][71][72]; and training or testing alternative ML glitch classification algorithms [57,[73][74][75][76][77][78][79]. Overall, Gravity Spy classifications have been instrumental in GW detector characterization, spanning from informal investigations to a key part of GW data analysis software [14]. ...

Reference:

Gravity Spy: lessons learned and a path forward
Detecting and diagnosing terrestrial gravitational-wave mimics through feature learning
  • Citing Article
  • March 2023

Physical Review D

... We leveraged state-of-the-art analytical advances in high-resolution mass spectrometry 16 to simultaneously profile thousands of potential environmental chemicals in seminal plasma, which is more proximal and relevant for male reproductive health compared to measures of chemicals in systemic circulation. 17,18 We then combined a novel machine learning pattern recognition approach, principal component pursuit (PCP), 19,20 with modern statistical mixtures analyses 21 to efficiently detect associations of environmental chemicals with male reproductive health. Typical studies model one feature (e.g., genetic polymorphism or environmental exposure) at a time, 22 repeated through all features, which incurs severe multiple testing penalties on statistical power. ...

Applying principal component pursuit to investigate the association between source-specific fine particulate matter and myocardial infarction hospitalizations in New York City

Environmental Epidemiology

... Recent machine learning-based approaches to glitch understanding and mitigation include works that investigate the association between glitches and LIGO's auxiliary data channels by casting glitch detection as a classification problem using only non-astrophysicallysensitive auxiliary channel data as input [42,43]. Many other glitch detection methods directly analyze the gravitational-wave strain [21, 23, 25, 30-32, 34-39, 44-49]. ...

Architectural optimization and feature learning for high-dimensional time series datasets
  • Citing Article
  • January 2023

Physical Review D

... We leveraged state-of-the-art analytical advances in high-resolution mass spectrometry 16 to simultaneously profile thousands of potential environmental chemicals in seminal plasma, which is more proximal and relevant for male reproductive health compared to measures of chemicals in systemic circulation. 17,18 We then combined a novel machine learning pattern recognition approach, principal component pursuit (PCP), 19,20 with modern statistical mixtures analyses 21 to efficiently detect associations of environmental chemicals with male reproductive health. Typical studies model one feature (e.g., genetic polymorphism or environmental exposure) at a time, 22 repeated through all features, which incurs severe multiple testing penalties on statistical power. ...

Principal Component Pursuit for Pattern Identification in Environmental Mixtures
  • Citing Article
  • November 2022

Environmental Health Perspectives

... We can deconstruct the major deviations from the optimal detection scenario into the following: unknown signal parameters, non-stationary noise, uncertainty in the estimates of noise power spectral density (PSD) and non-Gaussian noise artefacts. All of these factors contribute to the departure of matched-filtering from Neyman-Pearson optimality [25][26][27][28][29] to varying degrees [9,10]. ...

Generalized approach to matched filtering using neural networks
  • Citing Article
  • February 2022

Physical Review D

... Examples of ML algorithms to identify the origin of the noise artifacts and infer the relevant mechanical couplings in the detector were presented in Cavaglià et al (2018) and Colgan et al (2020). In these methods, event trigger generators operating on auxiliary channels provide input to ML binary classification algorithms like Random Forests, Genetic Programming, and logistic regression to either rank the channels according to their correlation to the GW channel (Cavaglià et al 2018) or produce a probability estimate to classify data periods as glitchy or clean (Colgan et al 2020). ...

Efficient gravitational-wave glitch identification from environmental data through machine learning
  • Citing Article
  • May 2020

Physical Review D

... [27][28][29][30] As an advanced electroanalytical scanning probe technique, SECM can quantify local electron transfer activity and topography changes with a high spatial and temporal resolution. [31][32][33][34] Additionally, it can also in situ detect the electrochemical response of the substrate surface under operating z E-mail: jshui@suda.edu.cn conditions due to its unique four-electrode system. ...

Probing the Speed Limits of Scanning Electrochemical Microscopy with In situ Colorimetric Imaging

... In the absence of kernel calibration, our setting takes the form of Blind Sparse Deconvolution (BSD) problem. In the prior art, BSD has been studied in various flavors including BSD via multichannel [36,58] and single-channel [38,59] methods. However, such BSD approaches do not translate to the ToF context due to 1) kernel priors e.g.incoherence [39], non-negativity [41] and short-support [59], 2) assumption that Dirac impulses or spikes lie on a grid [36,45,59], and 3) the large scale data that arises in ToF imaging [13,35]. ...

Geometry and Symmetry in Short-and-Sparse Deconvolution
  • Citing Article
  • February 2020

SIAM Journal on Mathematics of Data Science

... These type of machine learning denoising techniques have already been applied to fluorescence microscopy [11,17], ARPES [18,19] and transmission electron microscopy data [12,20]. Related are recent works focusing on the recovery of phase-sensitive information from full experimental QPI images, such as employing blind deconvolution [21] and multi-atom techniques [22]. * kuijf@lorentz.leidenuniv.nl ...

Dictionary learning in Fourier-transform scanning tunneling spectroscopy

... Convolutional Sparse Coding (CSC) model has gradually attracted attention in the field of image processing and computer vision. CSC model based on sparse representation theory [6,7,8,9,10], It is assumed that the input signal can be represented by a small number of atoms in the dictionary, leading to excellent performance in data compression and representation. This method can not only capture the intrinsic structure of the data, but also provide a certain understanding of the function of the network structure, and has been widely used [11]. ...

Structured Local Optima in Sparse Blind Deconvolution
  • Citing Article
  • September 2019

IEEE Transactions on Information Theory