My name is Madalina (Ina) Fiterau, I have obtained my PhD in Machine Learning from CMU in the Fall of 2015.
Currently, I am a Postdoctoral Scholar in the Computer Science Department at Stanford University and part of the Mobilize Center. My postdoctoral advisors are Professors Chris Ré and Scott Delp.
My PhD thesis advisor is Dr. Artur Dubrawski, head of the Auton Lab. I obtained my master's degree in Machine Learning from CMU in 2012.
My main interests are query-specific models for decision support systems, learning with structured sparsity, dimensionality reduction in an active learning setting and anomalous pattern detection. My current research explores the idea of building small ensembles of low-dimensional components which are applicable to significant subsets of data, such that any given sample can be handled using one of these sub-models or a sparse mixture of them. The methods I'm developing optimize the assignment of samples to sub-models while reducing the dimensionality of the solvers in the ensemble.
Application-wise, I am working on analysing vital sign data obtained by monitoring patients admitted to the Intensive Care Unit. I am generally interested in the use of machine learning systems for medical applications. This is the focus of the MLCDA NIPS workshop, which I co-organized in 2013 with Jenna Wiens and Finale Doshi-Velez, and the ML4CHG NIPS workshop, which I co-organized in 2014 with Julia Vogt and Gunnar Rätsch.
I started off as a software engineer, having received my BEng from Politehnica Timisoara, Romania in 2009. Designing and coding software systems is something I enjoy, which is one of the reasons why I've twice interned at Google, working with Jonathan Scott (summer of 2011) and Parisa Haghani (summer of 2013). I have also completed a research internship at Microsoft Research Cambridge, working with Peter Kontschieder.
- Regression for Informative Projection Retrieval (RIPR) - a regression-based algorithm which identifies informative projections by optimizing over a matrix of point-wise loss estimators, learning compact models for classification, clustering, and regression. The framework is currently being adapted to work in an active learning setting.
[ensemble methods; feature selection; projection retrieval; query-specific models]
- Application: Artifact adjudication for health status alerts. This is a collaborative project with a team from the University of Pittsburgh. We work with a cardio-respiratory monitoring system designed to process multiple vital signs indicative of the health status of ICU patients. The system issues an alert whenever some form of instability requires attention, but in practice, a substantial fraction of these alerts are artifacts. A subset of the data has been manually labeled and the aim is to use that subset to determine which of of the unlabeled samples are worth the experts' attention.
[active learning; dimensionality reduction; ensemble methods]
- Application: Detection of nuclear threats from vehicles scanned at the US border.
One of the many projects under way at the Auton Lab, this presents a multiclass discrimination problem where expert feedback is available.
The models need to be interpretable. Another interesting aspect of this dataset is that the training and test samples come from different distributions.
[multilabel classification; interpretable models; transductive learning]
- Vital Sign Monitoring System that predicts clinical alarms and detects anomalous patterns in patient vital signs.
This project uses the waveform and treatment data in the Mimic II dataset.
[dynamic Bayesian Networks; variational methods]
- Explanation-Oriented Partitioning - the task of finding sets of high-accuracy regions in low-dimensional subspaces. The framework we developed uses any given hypothesis class and enables visualization of the classification process.
[ensemble methods; query-specific models]
- Finding explanations in datasets by exploring areas in low-dimensional projections of the feature space.
I've implemented some heuristic approaches as well as LPs which explicitly minimize entropy-based objective functions.
[feature selection; information theory; linear programming]
Below are all my publications by year. View publication list
- Madalina Fiterau and Artur Dubrawski. Active learning for Informative Projection Recovery. In the Conference of the Association for the Advancement of Artificial Intelligence, volume 29, AAAI 2015. Spotlight and poster.
- Nick Gisolfi, Madalina Fiterau and Artur Dubrawski. Finding Meaningful Gaps to Guide Data Acquisition for a Radiation Adjudication System . In the Conference of the Association for the Advancement of Artificial Intelligence, volume 29, AAAI 2015. Spotlight and poster.
- Matt Barnes, Nick Gisolfi, Madalina Fiterau and Artur Dubrawski. Leveraging Common Structure to Improve Prediction across Related Datasets. In the Conference of the Association for the Advancement of Artificial Intelligence, volume 29, AAAI 2015. Spotlight and poster.
- Fiterau M, Dubrawski A, Chen L, Hravnak M, Bose E, Gilles C, Pinsky MR. Archetyping artifacts in monitored noninvasive vital signs data. Society of Critical Care Medicine Annual Congress 2015. Oral Presentation.
- Wang D, Fiterau M, Dubrawski A, Hravnak M, Clermont G and Pinsky MR. Interpretable active learning in support of clinical data annotation. Society of Critical Care Medicine Annual Congress 2015. Poster.
- Madalina Fiterau and Artur Dubrawski. Reducing Annotation Effort through Projection Retrieval in an Active Learning Setting. Women in Machine Learning Workshop, Montreal, Quebec, Canada, December 2014. Poster.
- Madalina Fiterau and Artur Dubrawski. Discovering Compact and Informative Structures through Data Partitioning. Thesis Proposal. CMU, ML Department, Fall 2014.
- Fiterau M, Dubrawski A, Chen L, Hravnak M, Clermont G, Bose E, Guillame-Bert M, Pinsky MR. Artifact adjudication for vital sign step-down unit data can be improved using Active Learning with low-dimensional models. Annual Congress of the European Society of Intensive Care Medicine 2014. Electronic poster.
- Wang D, Chen L, Fiterau M, Dubrawski A, Hravnak M, Bose E, Wallace D, Kaynar M, Clermont G, Pinsky MR. Multi-tier ground truth elicitation framework with application to artifact classification for predicting patient instability. Annual Congress of the European Society of Intensive Care Medicine 2014. Electronic poster.
- Hravnak M, Chen L, Dubrawski A, Clermont G, Bose E, Fiterau M, Guillame-Bert M, Pinsky MR. Supervised Machine learning can classify artifact in multi-signal vital sign monitoring data from Step-Down Unit (SDU) Patients. Annual Congress of the European Society of Intensive Care Medicine 2014.
- Hravnak M, Chen L, Fiterau M, Dubrawski A, Clermont G, Guillame-Bert M, Bose E, Pinsky MR. Active machine learning to increase annotation efficiency in classifying vital sign events as artifact or real alerts in continuous noninvasive monitoring. American Journal of Respiratory and Critical Care Medicine 189; 2014:A3627. Oral Presentation.
- Nicholas Gisolfi, Madalina Fiterau and Artur Dubrawski. Finding Gaps in Data to Guide Development of a Radiation Threat Adjudication System. 2014 Symposium on Radiation Measurements and Applications. Poster.
- Madalina Fiterau and Artur Dubrawski. Informative projection recovery for classification, clustering and regression. In International Conference on Machine Learning and Applications, volume 12, ICMLA 2013. Oral Presentation.
- Fiterau M, Dubrawski A, Chen L, Hravnak M, Clermont G, Pinsky MR. Automatic identification of artifacts in monitoring critically ill patients. Annual Congress of the European Society of Intensive Care Medicine 2014; 39 Suppl 2: S470. Electronic Poster.
- Madalina Fiterau and Artur Dubrawski. Detecting Artifacts in Clinical Data through Projection Retrieval. ICML Workshop on the Role of Machine Learning in Transforming Healthcare: Recent progress, Challenges and Opportunities, June 2013, Atlanta. Spotlight and poster.
- Madalina Fiterau and Artur Dubrawski. An Application of Divergence Estimation to Projection Retrieval for Semi-supervised Classification and Clustering, ICML Workshop on Divergences and Divergence Learning. June 2013, Atlanta. Oral Presentation.
- Madalina Fiterau and Artur Dubrawski. Explaining Datasets through High-Accuracy Regions. Women in Machine Learning Workshop, Granada, Spain, December 2011. Oral presentation.
- Madalina Fiterau, Artur Dubrawski, Can Ye, Real-time Adaptive Monitoring of Vital Signs for Clinical Alarm Preemption, international Society for Disease Surveillance Annual Conference 2011. Poster.
- Madalina Fiterau, Andrew Sheng, Venkat Senapati, Nagasrikanth Kallakuri, Robert Walzer Real-time Algorithmic Detection of a Landing Site using Sensors aboard a Lunar Lander, Technical Report, Advanced Mobile Robot Development, CMU, Spring 2011.
- Madalina Fiterau, Olga Ormond, Gabriel-Miro Muntean, Performance of Handover for Multiple Users in Heterogeneous Wireless Networks, IEEE Conference on Local Computer Networks 2009. Poster.
- Madalina Fiterau, Dr. Gabriel-Miro Muntean, Prof. Ioan Jurca, Handover Algorithm Design and Simulation, Diploma Project, Bachelors in Computer Engineering, Politehnica University of Timisoara, July 2009.
PhD Student in Machine Learning
Carnegie Mellon University
5000 Forbes Ave.
6105 Gates-Hillman Complex
Pittsburgh, PA 15213
office phone: 412-268-3370
To obtain my e-mail address
, run the following script
in the python interpreter:
''.join([x for s in map(lambda(x): x[0:x.find('ad') if x.find('ad')>=0 else len(x)],list(['madalina','fiterau'])) + zip(list(['@','.','.']),list(['cs','cmu','edu'])) for x in s])
In case you don't have python handy (seriously?), my e-mail address is username@domain
where my username is on the URL of the page (after ~) and the domain is cs.cmu.edu.
14th of July 2016
VIPR demo presented at IJCAI 2016.
View website | camera ready | poster.
12th of July 2016
Deep Neural Decision Forests presented at IJCAI 2016.
View camera ready | slides.
22nd of February 2016
Expert study for RIPR presented at SCCM 2016.
View abstract | slides.
14th of December 2015
Deep Neural Decision Forests wins Marr prize for Best Paper at ICCV 2015.
View camera ready | spotlight | poster.
27th of January 2015
The ActiveRIPR framework was presented at AAAI 2015.
view camera ready | poster.
18th of January 2015
The research on archetyping artifacts from alerts in vital sign monitoring data was presented at SCCM.
12th of December 2014
The 2nd Workshop on Machine Learning for Clinical Data Analysis, Healthcare and Genomics took place at NIPS.
Many thanks to our speakers, panelists, poster presenters, and PC members!
27th of October 2014
Completed thesis proposal, Discovering Compact and Informative Structures through Data Partitioning.
Many thanks to my committee members and collaborators!
10th of December 2013
The Machine Learning for Clinical Data Analysis Workshop took place at NIPS.
Many thanks to our speakers, panelists, poster presenters and PC members!
4th of December 2013
The RIPR algorithm presented at ICMLA 2013.
view camera ready and slides.
30th of September 2013
The paper Automatic Identification of Alarm Artifacts in Monitoring Critically Ill Patients presented at ESICM-LIVES.
view electronic poster.
20th of June 2013
RIPR models for artifact adjudication shown at the ICML-HEALTH Workshop.
view camera ready | poster.
3rd of December 2012
The RECIP algorithm was shown at NIPS 2012.
view camera ready | poster.
3rd of December 2012
'Feature-Task Co-clustering Regression' was presented at WiML 2012.
view abstract | poster.
21st of March 2012
Data Analysis Project. Committee: Prof. Artur Dubrawski, Prof. Geoff Gordon, Prof. Jeff Schneider
view slides pptx|pdf.
12th of December 2011
the algorithm `Explanation-Oriented Partitioning' was presented at the WiML workshop in Granada.
7th of December 2011
the paper `Real-time Adaptive Monitoring of Vital Signs for Clinical Alarm Preemption' presented at the iSDS Annual Conference in Atlanta.
29th of November 2011
Aiming for the Moon, an outline of the Lander visual registering project was presented during the ML Journal Club.