Automated Machine Learning and Data Science [AMLDS]       

links

Automated Machine Learning and Data Science [AMLDS] Publications



2017

Automatic Frankensteining: Creating Complex Ensembles Autonomously
Martin Wistuba, Nicolas Schilling, Lars Schmidt-Thieme
Proceedings of the SIAM International Conference on Data Mining (SDM), pp. 741-749, 2017


Foresight: Recommending Visual Insights [Demo and Workshop]
Cagatay Demiralp, PeterJ. Haas, Srinivasan Parthasarathy, Tejaswini Pedapati
VLDB Demo Track. This paper has also been accepted for oral presentation at KDD IDEA 2017 Workshop.

REMIX: Automated Exploration for Interactive Outlier Detection
Yanjie Fu, Charu Aggarwal, Srinivasan Parthasarathy, Deepak S. Turaga, Hui Xiong
23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2017

Outlier Detection with Autoencoder Ensembles
Chen, Jinghui and Sathe, Saket and Aggarwal, Charu and Turaga, Deepak
Proceedings of the 2017 SIAM International Conference on Data Mining, pp. 90--98
Abstract

Feature Engineering for Predictive Modeling using Reinforcement Learning
Khurana, Udayan and Samulowitz, Horst and Turaga, Deepak
arXiv preprint arXiv:1709.07150, 2017
Abstract

System and Apparatus for Automatic Feature Engineering from Relational Databases for Predictive Modelling
Thanh Lam Hoang, Inventor Johann-Michael Thiebaut, Tiep Mai, Bei Chen, MATHIEU SINN


2016

Hyperparameter Optimization Machines
Martin Wistuba, Nicolas Schilling, Lars Schmidt-Thieme
IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 41-50, 2016

Two-Stage Transfer Surrogate Model for Automatic Hyperparameter Optimization
Martin Wistuba, Nicolas Schilling, Lars Schmidt-Thieme
Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), pp. 199-214, 2016

Scalable Hyperparameter Optimization with Products of Gaussian Process Experts
Nicolas Schilling, Martin Wistuba, Lars Schmidt-Thieme
Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), pp. 33-48, 2016

Selecting Near-Optimal Learners via Incremental Data Allocation.
Sabharwal, Ashish and Samulowitz, Horst and Tesauro, Gerald
AAAI, pp. 2007--2015, 2016
Abstract

Deep Learning for Algorithm Portfolios.
Loreggia, Andrea and Malitsky, Yuri and Samulowitz, Horst and Saraswat, Vijay A
AAAI, pp. 1280--1286, 2016
Abstract

Adaptive data augmentation for image classification
Fawzi, Alhussein and Samulowitz, Horst and Turaga, Deepak and Frossard, Pascal
Image Processing (ICIP), 2016 IEEE International Conference on, pp. 3688--3692
Abstract

Image inpainting through neural networks hallucinations
Fawzi, Alhussein and Samulowitz, Horst and Turaga, Deepak and Frossard, Pascal
Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), 2016 IEEE 12th, pp. 1--5
Abstract

Automating Feature Engineering
Udayan Khurana, Fatemeh Nargesian, Horst Samulowitz, Elias Khalil, Deepak Turaga
NIPS workshop on Artificial Intelligence for Data Science, 2016


AUTOMATIC ENUMERATION OF DATA ANALYSIS OPTIONS AND RAPID ANALYSIS OF STATISTICAL MODELS
Khurana, Udayan and Parthasarathy, Srinivasan and Pavuluri, Venkata N and Turaga, Deepak S and Vu, Long H
US Patent 20,160,110,410


Graph-based Exploration of Non-graph Datasets [Demo]
Udayan Khurana, Srinivasan Parthasarathy, Deepak S. Turaga
VLDB Demo Paper, 2016


2015

Hyperparameter Optimization with Factorized Multilayer Perceptrons
Nicolas Schilling, Martin Wistuba, Lucas Drumond, Lars Schmidt-Thieme
Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), pp. 87-103, 2015

Hyperparameter Search Space Pruning - A New Component for Sequential Model-Based Hyperparameter Optimization
Martin Wistuba, Nicolas Schilling, Lars Schmidt-Thieme
Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), pp. 104-119, 2015

Learning Hyperparameter Optimization Initializations
Martin Wistuba, Nicolas Schilling, Lars Schmidt-Thieme
IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 1-10, 2015

Sequential Model-Free Hyperparameter Tuning
Martin Wistuba, Nicolas Schilling, Lars Schmidt-Thieme
IEEE International Conference on Data Mining (ICDM), pp. 1033-1038, 2015

Learning Data Set Similarities for Hyperparameter Optimization Initializations.
Martin Wistuba, Nicolas Schilling, Lars Schmidt-Thieme
Proceedings of the 2015 International Workshop on Meta-Learning and Algorithm Selection co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, pp. 15-26

Joint Model Choice and Hyperparameter Optimization with Factorized Multilayer Perceptrons
Nicolas Schilling, Martin Wistuba, Lucas Drumond, Lars Schmidt-Thieme
IEEE 27th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 72-79, 2015

Deep Learning for Algorithm Portfolios
Andrea Loreggia, Yuri Malitsky, Horst Samulowitz, Vijay Saraswat
2015 - cs.toronto.edu

Automated intelligent data navigation and prediction tool
Klinger, Tamir and Reddy, Chandrasekhara K and Sabharwal, Ashish and Samulowitz, Horst C and Tesauro, Gerald J and Turaga, Deepak S
US Patent App. 14/812,344
Abstract

Budgeted Prediction with Expert Advice.
Amin, Kareem and Kale, Satyen and Tesauro, Gerald and Turaga, Deepak S
AAAI, pp. 2490--2496, 2015
Abstract

Towards Cognitive Automation of Data Science.
A.Biem, M.Butrico, M.Feblowitz, T.Klinger, Y.Malitsky, K.Ng, A.Perer, C.Reddy, A.Riabov, H.Samulowitz, D.Sow, G.Tesauro, D.Turaga
AAAI, pp. 4268--4269, 2015


2014

Large Scale Discriminative Metric Learning
Peter D. Kirchner, Matthias Boehm, Berthold Reinwald, Daby M. Sow, Michael Schmidt, Deepak S. Turaga, Alain Biem
ParLearning, 2014


2013

Managing a portfolio of experts
Stern, David and Samulowitz, Horst Cornelius and Herbrich, Ralf and Graepel, Thore
US Patent 8,433,660
Abstract

Resolution and parallelizability: barriers to the effficient parallelization of SAT solvers
Sabharwal, Ashish and Samulowitz, Horst and Simon, Laurent and others
Twenty-Seventh AAAI Conference on Artificial Intelligence. 2013; AAAI 2013-27th AAAI Conference, Bellevue, USA, 2013-07-14-2013-07-18,
Abstract

Real-time analysis and management of big time-series data
Alain Biem, Hanhua Feng, AV Riabov, Deepak S Turaga
IBM Journal of Research and Development 57(3/4), 8--1, IBM, 2013

Stronger inference through implied literals from conflicts and knapsack covers
Tobias Achterberg, Ashish Sabharwal, Horst Samulowitz
Integration of AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems, pp. 1--11, Springer, 2013

Boosting Sequential Solver Portfolios: Knowledge Sharing and Accuracy Prediction
Yuri Malitsky, Ashish Sabharwal, Horst Samulowitz, Meinolf Sellmann
Learning and Intelligent Optimization, pp. 153--167, Springer, 2013

Snappy: A simple algorithm portfolio
Horst Samulowitz, Chandra Reddy, Ashish Sabharwal, Meinolf Sellmann
Theory and Applications of Satisfiability Testing--SAT 2013, pp. 422--428, Springer

Algorithm portfolios based on cost-sensitive hierarchical clustering
Yuri Malitsky, Ashish Sabharwal, Horst Samulowitz, Meinolf Sellmann
Proceedings of the Twenty-Third international joint conference on Artificial Intelligence, pp. 608--614, 2013

Automated Design of Search with Composability
Ashish Sabharwal, Horst Samulowitz, Tom Schrijvers, Peter J Stuckey, Guido Tack
Workshops at the Twenty-Seventh AAAI Conference on Artificial Intelligence, 2013


2012

Parallel SAT solver selection and scheduling
Yuri Malitsky, Ashish Sabharwal, Horst Samulowitz, Meinolf Sellmann
Principles and Practice of Constraint Programming, pp. 512--526, 2012

Augmenting clause learning with implied literals
Arie Matsliah, Ashish Sabharwal, Horst Samulowitz
Theory and Applications of Satisfiability Testing--SAT 2012, pp. 500--501, Springer

SatX10: A Scalable Plug&Play Parallel SAT Framework
Bard Bloom, David Grove, Benjamin Herta, Ashish Sabharwal, Horst Samulowitz, Vijay Saraswat
Theory and Applications of Satisfiability Testing -- SAT 2012, Lecture Notes in Computer Science, pp. 463-468, Springer
Abstract

An Introduction to Temporal Graph Data Management
Khurana, Udayan
Technical Report, Technical report, May, 2012

Guiding combinatorial optimization with UCT
Ashish Sabharwal, Horst Samulowitz, Chandra Reddy
Integration of AI and OR Techniques in Contraint Programming for Combinatorial Optimzation Problems, 356--361, Springer, 2012


2011

Algorithm selection and scheduling
Serdar Kadioglu, Yuri Malitsky, Ashish Sabharwal, Horst Samulowitz, Meinolf Sellmann
Principles and Practice of Constraint Programming--CP 2011, 454--469, Springer

Non-model-based algorithm portfolios for SAT
Yuri Malitsky, Ashish Sabharwal, Horst Samulowitz, Meinolf Sellmann
Theory and Applications of Satisfiability Testing-SAT 2011, 369--370, Springer


2010

Towards a lightweight standard search language
Horst Samulowitz, Guido Tack, Julien Fischer, Mark Wallace, Peter Stuckey
Constraint Modeling and Reformulation (ModRef’10), 2010

Collaborative expert portfolio management
David Stern, Ralf Herbrich, Thore Graepel, Horst Samulowitz, Luca Pulina, Armando Tacchella
Proc. of AAAI, pp. 210--216, 2010


2009

Experiments with massively parallel constraint solving
Lucas Bordeaux, Youssef Hamadi, Horst Samulowitz
Proceedings of the 21st international jont conference on Artifical intelligence, pp. 443--448, 2009

Learning adaptation to solve constraint satisfaction problems
Yuehua Xu, David Stern, Horst Samulowitz
Proc. of Third Workshop on Learning and Intelligent Optimization (LION’03), Trento, Italy, 2009


2007

On the stochastic constraint satisfaction framework
Lucas Bordeaux, Horst Samulowitz
Proceedings of the 2007 ACM symposium on Applied computing, pp. 316--320

Dynamically partitioning for solving QBF
Horst Samulowitz, Fahiem Bacchus
Theory and Applications of Satisfiability Testing--SAT 2007, 215--229, Springer

Learning to solve QBF
Horst Samulowitz, Roland Memisevic
Proceedings of the national conference on artificial intelligence, pp. 255, 2007




Automated Machine Learning and Data Science

Check out some features here: https://datascience.ibm.com/