@conference{nokey,

title = {Principal Component Flows},

author = {Edmond Cunningham, Adam D Cobb, Susmit Jha},

url = {https://proceedings.mlr.press/v162/cunningham22a.html},

year  = {2022},

date = {2022-07-17},

urldate = {2022-07-17},

abstract = {Normalizing flows map an independent set of latent variables to their samples using a bijective transformation. Despite the exact correspondence between samples and latent variables, their high level relationship is not well understood. In this paper we characterize the geometric structure of flows using principal manifolds and understand the relationship between latent variables and samples using contours. We introduce a novel class of normalizing flows, called principal component flows (PCF), whose contours are its principal manifolds, and a variant for injective flows (iPCF) that is more efficient to train than regular injective flows. PCFs can be constructed using any flow architecture, are trained with a regularized maximum likelihood objective and can perform density estimation on all of their principal manifolds. In our experiments we show that PCFs and iPCFs are able to learn the principal manifolds over a variety of datasets. Additionally, we show that PCFs can perform density estimation on data that lie on a manifold with variable dimensionality, which is not possible with existing normalizing flows. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Deznabi2021b,

title = {Predicting in-hospital mortality by combining clinical notes with time-series data},

author = {Iman Deznabi, Mohit Iyyer, Madalina Fiterau},

url = {https://aclanthology.org/2021.findings-acl.352.pdf},

year  = {2021},

date = {2021-08-06},

urldate = {2021-08-06},

booktitle = {Association for Computational Linguistics (ACL-IJCNLP 2021) Findings},

abstract = {In intensive care units (ICUs), patient health is monitored through (1) continuous vital signals from various medical devices, and (2) clinical notes consisting of opinions and summaries from doctors which are recorded in electronic health records (EHR). It is difficult to jointly model these two sources of information because clinical notes, unlike vital signals, are collected at irregular intervals and their contents are relatively unstructured. In this paper, we present a model that combines both sources of information about ICU patients to make accurate in-hospital mortality predictions. We apply a fine-tuned BERT model to each of the patient's clinical notes. The resulting embeddings are then combined to obtain the overall embedding for the entire text part of the data. This is then combined with the output of an LSTM model that encodes patients' vital signals. Our model improves upon the state of the art for mortality prediction, attaining an AUC score of 0.9, compared to the previous 0.87, setting a new standard for mortality prediction on the MIMIC III benchmark.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {A Change of Variables Method For Rectangular Matrix-Vector Products},

author = {Edmond Cunningham, Madalina Fiterau},

url = {https://proceedings.mlr.press/v130/cunningham21a.html},

year  = {2021},

date = {2021-04-13},

abstract = {Rectangular matrix-vector products (MVPs) are used extensively throughout machine learning and are fundamental to neural networks such as multi-layer perceptrons. However, the use of rectangular MVPs in successive normalizing flow transformations is notably missing. This paper identifies this methodological gap and plugs it with a tall and wide MVP change of variables formula. Our theory builds up to a practical algorithm that envelops existing dimensionality increasing flow methods such as augmented flows. We show that tall MVPs are closely related to the stochastic inverse of wide MVPs and empirically demonstrate that they improve density estimation over existing dimension changing methods. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}