Greg Ver Steeg

Prof. Greg Ver Steeg

University of Southern California
orcid

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 June 2019 in Scientific Data
Verified
Journal Article
Open access
PDF file
HHHrayr Harutyunyan
Hrayr Harutyunyan
HKHrant Khachatrian
Hrant Khachatrian
DKDavid C. Kale
David C. Kale
Greg Ver SteegGreg Ver Steeg
Greg Ver Steeg
AGAram Galstyan
Aram Galstyan
Health care is one of the most exciting frontiers in data mining and machine learning. Successful adoption of electronic health records (EHRs) created an explosion in digital clinical data available for analysis, but progress in machine learning for healthcare research has been difficult to measure because of the absence of publicly available benchmark data sets. To address this problem, we propose four clinical prediction benchmarks using data derived from the publicly available Medical Information Mart for Intensive Care (MIMIC-III) database. These tasks cover a range of clinical problems including modeling risk of mortality, forecasting length of stay, detecting physiologic decline, and phenotype classification. We propose strong linear and neural baselines for all four tasks and evaluate the effect of deep supervision, multitask training and data-specific architectural modifications on the performance of neural models.

23 February 2009 in Physical Review D
Verified
Journal Article
Closed access
PDF file
Greg Ver SteegGreg Ver Steeg
Greg Ver Steeg
NMNicolas C. Menicucci
Nicolas C. Menicucci
We show that entanglement can be used to detect spacetime curvature. Quantum fields in the Minkowski vacuum are entangled with respect to local field modes. This entanglement can be swapped to spatially separated quantum systems using standard local couplings. A single, inertial field detector in the exponentially expanding (de Sitter) vacuum responds as if it were bathed in thermal radiation in a Minkowski universe. We show that using two inertial detectors, interactions with the field in the thermal case will entangle certain detector pairs that would not become entangled in the corresponding de Sitter case. The two universes can thus be distinguished by their entangling power.

13 July 2016 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
LZLinhong Zhu
Linhong Zhu
DGDong Guo
Dong Guo
JYJunming Yin
Junming Yin
Greg Ver SteegGreg Ver Steeg
Greg Ver Steeg
AGAram Galstyan
Aram Galstyan
We propose a temporal latent space model for link prediction in dynamic social networks, where the goal is to predict links over time based on a sequence of previous graph snapshots. The model assumes that each user lies in an unobserved latent space, and interactions are more likely to occur between similar users in the latent space representation. In addition, the model allows each user to gradually move its position in the latent space as the network structure evolves over time. We present a global optimization algorithm to effectively infer the temporal latent space. Two alternative optimization algorithms with local and incremental updates are also proposed, allowing the model to scale to larger networks without compromising prediction accuracy. Empirically, we demonstrate that our model, when evaluated on a number of real-world dynamic networks, significantly outperforms existing approaches for temporal link prediction in terms of both scalability and predictive power.

1 December 2017 in Transactions of the Association for Computational Linguistics
Verified
Journal Article
Open access
RGRyan J. Gallagher
Ryan J. Gallagher
KRKyle Reing
Kyle Reing
DKDavid Kale
David Kale
Greg Ver SteegGreg Ver Steeg
Greg Ver Steeg
While generative models such as Latent Dirichlet Allocation (LDA) have proven fruitful in topic modeling, they often require detailed assumptions and careful specification of hyperparameters. Such model complexity issues only compound when trying to generalize generative models to incorporate human input. We introduce Correlation Explanation (CorEx), an alternative approach to topic modeling that does not assume an underlying generative model, and instead learns maximally informative topics through an information-theoretic framework. This framework naturally generalizes to hierarchical and semi-supervised extensions with no additional modeling assumptions. In particular, word-level domain knowledge can be flexibly incorporated within CorEx through anchor words, allowing topic separability and representation to be promoted with minimal human intervention. Across a variety of datasets, metrics, and experiments, we demonstrate that CorEx produces topics that are comparable in quality to those produced by unsupervised and semi-supervised variants of LDA.

6 April 2020 in Magnetic Resonance in Medicine
Verified
Journal Article
Open access
PDF file
DMDaniel Moyer
Daniel Moyer
Greg Ver SteegGreg Ver Steeg
Greg Ver Steeg
CTChantal M. W. Tax
Chantal M. W. Tax
PTPaul M. Thompson
Paul M. Thompson
Purpose: In the present work, we describe the correction of diffusion‐weighted MRI for site and scanner biases using a novel method based on invariant representation.Theory and Methods: Pooled imaging data from multiple sources are subject to variation between the sources. Correcting for these biases has become very important as imaging studies increase in size and multi‐site cases become more common. We propose learning an intermediate representation invariant to site/protocol variables, a technique adapted from information theory‐based algorithmic fairness; by leveraging the data processing inequality, such a representation can then be used to create an image reconstruction that is uninformative of its original source, yet still faithful to underlying structures. To implement this, we use a deep learning method based on variational auto‐encoders (VAE) to construct scanner invariant encodings of the imaging data.Results: To evaluate our method, we use training data from the 2018 MICCAI Computational Diffusion MRI (CDMRI) Challenge Harmonization dataset. Our proposed method shows improvements on independent test data relative to a recently published baseline method on each subtask, mapping data from three different scanning contexts to and from one separate target scanning context.Conclusions: As imaging studies continue to grow, the use of pooled multi‐site imaging will similarly increase. Invariant representation presents a strong candidate for the harmonization of these data.

16 April 2012
Verified
Conference Paper
Open access
PDF file
Greg Ver SteegGreg Ver Steeg
Greg Ver Steeg
AGAram Galstyan
Aram Galstyan