327 citations · 1.2k across the 24 of their papers we have counts for
24 papers
SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer
Renan A. Rojas-Gomez, Karan Singhal, Ali Etemad +3
Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with…
Random Field Augmentations for Self-Supervised Representation Learning
Philip Andrew Mansfield, Arash Afkanpour, Warren Richard Morningstar +1
Self-supervised representation learning is heavily dependent on data augmentations to specify the invariances encoded in representations. Previous work has shown that applying dive…
Towards Federated Learning Under Resource Constraints via Layer-wise Training and Depth Dropout
Pengfei Guo, Warren Richard Morningstar, Raviteja Vemulapalli +3
Large machine learning models trained on diverse data have recently seen unprecedented success. Federated learning enables training on private data that may otherwise be inaccessib…
Federated Variational Inference: Towards Improved Personalization and Generalization
Elahe Vedadi, Joshua V. Dillon, Philip Andrew Mansfield +3
Conventional federated learning algorithms train a single global model by leveraging all participating clients' data. However, due to heterogeneity in client generative distributio…
Weighted Ensemble Self-Supervised Learning
Yangjun Ruan, Saurabh Singh, Warren Morningstar +4
Ensembling has proven to be a powerful technique for boosting model performance, uncertainty estimation, and robustness in supervised learning. Advances in self-supervised learning…
Federated Training of Dual Encoding Models on Small Non-IID Client Datasets
Raviteja Vemulapalli, Warren Richard Morningstar, Philip Andrew Mansfield +4
Dual encoding models that encode a pair of inputs are widely used for representation learning. Many approaches train dual encoding models by maximizing agreement between pairs of e…
What Do We Mean by Generalization in Federated Learning?
Honglin Yuan, Warren Morningstar, Lin Ning +1
Federated learning data is drawn from a distribution of distributions: clients are drawn from a meta-distribution, and their data are drawn from local data distributions. Thus gene…
VIB is Half Bayes
Alexander A Alemi, Warren R Morningstar, Ben Poole +2
In discriminative settings such as regression and classification there are two random variables at play, the inputs X and the targets Y. Here, we demonstrate that the Variational I…
Hunting for Dark Matter Subhalos in Strong Gravitational Lensing with Neural Networks
Joshua Yao-Yu Lin, Hang Yu, Warren Morningstar +2
Dark matter substructures are interesting since they can reveal the properties of dark matter. Collisionless N-body simulations of cold dark matter show more substructures compared…
PAC-Bayes: Narrowing the Empirical Risk Gap in the Misspecified Bayesian Regime
Warren R. Morningstar, Alexander A. Alemi, Joshua V. Dillon
The Bayesian posterior minimizes the "inferential risk" which itself bounds the "predictive risk". This bound is tight when the likelihood and prior are well-specified. However sin…
Density of States Estimation for Out-of-Distribution Detection
Warren R. Morningstar, Cusuh Ham, Andrew G. Gallagher +3
Perhaps surprisingly, recent studies have shown probabilistic model likelihoods have poor specificity for out-of-distribution (OOD) detection and often assign higher likelihoods to…
Automatic Differentiation Variational Inference with Mixtures
Warren R. Morningstar, Sharad M. Vikram, Cusuh Ham +2
Automatic Differentiation Variational Inference (ADVI) is a useful tool for efficiently learning probabilistic models in machine learning. Generally approximate posteriors learned…
Source structure and molecular gas properties from high-resolution CO imaging of SPT-selected dusty star-forming galaxies
Chenxing Dong, Justin S. Spilker, Anthony H. Gonzalez +17
We present Atacama Large Millimeter/submillimeter Array (ALMA) observations of high-J CO lines (, 7, 8) and associated dust continuum towards five strongly lensed,…
Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
Warren R. Morningstar, Laurence Perreault Levasseur, Yashar D. Hezaveh +6
We present a machine learning method for the reconstruction of the undistorted images of background sources in strongly lensed systems. This method treats the source as a pixelated…
Spatially Resolved [CII] Emission in SPT0346-52: A Hyper-Starburst Galaxy Merger at z~5.7
Katrina C. Litke, Daniel P. Marrone, Justin S. Spilker +18
SPT0346-52 is one of the most most luminous and intensely star-forming galaxies in the universe, with L_FIR > 10^13 L_sol and Sigma_SFR ~ 4200 M_sol yr^-1 kpc^-2. In this paper, we…
Analyzing interferometric observations of strong gravitational lenses with recurrent and convolutional neural networks
Warren R. Morningstar, Yashar D. Hezaveh, Laurence Perreault Levasseur +4
We use convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to estimate the parameters of strong gravitational lenses from interferometric observations. We exp…
A massive core for a cluster of galaxies at a redshift of 4.3
T. B. Miller, S. C. Chapman, M. Aravena +35
Massive galaxy clusters are now found as early as 3 billion years after the Big Bang, containing stars that formed at even earlier epochs. The high-redshift progenitors of these ga…
Galaxy growth in a massive halo in the first billion years of cosmic history
D. P. Marrone, J. S. Spilker, C. C. Hayward +34
According to the current understanding of cosmic structure formation, the precursors of the most massive structures in the Universe began to form shortly after the Big Bang, in reg…
Detection of lensing substructure using ALMA observations of the dusty galaxy SDP.81
Yashar D. Hezaveh, Neal Dalal, Daniel P. Marrone +13
We study the abundance of substructure in the matter density near galaxies using ALMA Science Verification observations of the strong lensing system SDP.81. We present a method to…
High Resolution Chandra HETG spectroscopy of V404 Cygni in Outburst
Ashley L. King, Jon M. Miller, John Raymond +2
As one of the best-characterized stellar-mass black holes, with good measurements of its mass, distance and inclination, V404 Cyg is the ideal candidate to study Eddington-limited…
Globular Cluster Systems in Brightest Cluster Galaxies: A Near-Universal Luminosity Function?
William E. Harris, Warren Morningstar, Oleg Y. Gnedin +10
We present the first results from our HST Brightest Cluster Galaxy (BCG) survey of seven central supergiant cluster galaxies and their globular cluster (GC) systems. We measure a t…
The spin of the black hole 4U 1543-47
W. R. Morningstar, J. M. Miller
We present a new analysis of Rossi X-ray Timing Explorer observations of the 2002 outburst of the transient X-ray nova 4U 1543-47. We focus on observations in the High/Soft state,…
A Seyfert-2-like Spectrum in the High-Mass X-ray Binary Microquasar V4641 Sgr
W. R. Morningstar, J. M. Miller, M. T. Reynolds +1
We present an analysis of three archival Chandra observations of the black hole V4641 Sgr, performed during a decline into quiescence. The last two observations in the sequence can…
The Spin of the Black Hole GS 1124-683: Observation of a Retrograde Accretion Disk?
Warren R. Morningstar, Jon M. Miller, Rubens C. Reis +1
We re-examine archival Ginga data for the black hole binary system GS 1124-683, obtained when the system was undergoing its 1991 outburst. Our analysis estimates the dimensionless…