Accepted talks and papers

Invited talks

- Chelsea Finn
- Zoubin Ghahramani
- Luc de Raedt

Accepted papers

37 Richard Liaw, Eric Liang, Robert Nishihara, Philipp Moritz, Joseph Gonzalez and Ion Stoica.

Demo Tune: A Research Platform for Distributed Model Selection and Training Paper

50 Jorge G Madrid, Hugo J Escalante, Eduardo Morales, Wei Wei Tu, Yang Yu, Lisheng Sun-Hosoya, Isabelle Guyon and Michele Sebag.

Towards AutoML in the presence of Drift: first results (Contributed Talk 3) Paper

6 Casey Davis and Christophe Giraud-Carrier.

Annotative Experts for Hyperparameter Selection Paper

7 Kunkun Pang, Mingzhi Dong, Yang Wu and Timothy Hospedales.

Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning (Contributed Talk 2) Paper

12 Mark McLeod, Michael A. Osborne and Stephen J Roberts.

Adaptive Quadrature for Fast Sequential Hyperparameter Marginalization Paper

19 Esteban Real, Alok Aggarwal, Yanping Huang and Quoc V. Le.

Evolutionary Algorithms and Reinforcement Learning: A Comparative Case Study for Architecture Search (Contributed Talk 4) Paper

35 Iddo Drori, Yamuna Krishnamurthy, Remi Rampin, Raoni de Paula Lourenco, Jorge Piazentin Ono, Kyunghyun Cho, Claudio Silva and Juliana Freire.

AlphaD3M: Machine Learning Pipeline Synthesis (Contributed Talk 1) Paper

43 Scott Langevin, David Jonker, Chris Bethune, Glen Coppersmith, Casey Hilland, Jonathon Morgan, Paul Azunre and Justin Gawrilow.

Demo Distil: A Mixed-Initiative Model Discovery System for Subject Matter Experts Paper

8 Erin Grant, Ghassen Jerfel, Katherine Heller and Thomas L. Griffiths.

Augmenting Gradient-Based Meta-Learning with Latent Variables to Capture Task Heterogeneity Paper

17 Yolanda Gil, Ke-Thia Yao, Varun Ratnakar, Daniel Garijo, Greg Ver Steeg, Pedro Szekely, Robert Brekelmans, Mayank Kejriwal, Fanghao Luo and I-Hui Huang.

P4ML: A Phased Performance-Based Pipeline Planner for Automated Machine Learning Paper

4 Janek Thomas, Stefan Coors and Bernd Bischl.

Demo Automatic Gradient Boosting Paper

9 Haifeng Jin, Qingquan Song and Xia Hu.

Demo Efficient Neural Architecture Search with Network Morphism Paper

13 Matthias Feurer, Benjamin Letham and Eytan Bakshy.

Scalable Meta-Learning for Bayesian Optimization using Ranking-Weighted Gaussian Process Ensembles Paper

16 Prajit Ramachandran and Quoc Le.

Dynamic Network Architectures Paper

22 Christos Tsirigotis, Xavier Bouthillier, François Corneau-Tremblay, Dendi Suhubdy, Frédéric Bastien and Pascal Lamblin.

Demo Orion: Experiment Version Control for Efficient Hyperparameter Optimization Paper

26 Eleni Nisioti, Kyriakos Chatzidimitriou and Andreas Symeonidis.

Predicting hyperparameters from meta-features in binary classification problems Paper

29 Jonathan Gordon, John Bronskill, Matthias Bauer, Sebastian Nowozin and Richard Turner.

Decision-Theoretic Meta-Learning: Versatile and Efficient Amortization of Few-Shot Learning Paper

40 Gellert Weisz, Andras Gyorgy and Csaba Szepesvari.

CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration Paper

46 Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer and Frank Hutter.

Practical Automated Machine Learning for the AutoML Challenge 2018 Paper

47 Paul Azunre, Craig Corcoran, David Sullivan, Garrett Honke, Rebecca Ruppel, Sandeep Verma and Jonathon Morgan.

Abstractive Tabular Dataset Summarization via Knowledge Base Semantic Embeddings Paper

49 Arber Zela, Aaron Klein, Stefan Falkner and Frank Hutter.

Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search Paper

51 Matthias Feurer and Frank Hutter.

Towards Further Automation in AutoML Paper

52 Brandon Schoenfeld, Christophe Giraud-Carrier, Mason Poggeman, Jarom Christensen and Kevin Seppi.

Preprocessor Selection for Machine Learning Pipelines Paper

55 Purushotham Kamath, Abhishek Singh and Debo Dutta.

Demo AMLA: an AutoML frAmework for Neural Network Design Paper

56 Neil Dhir, Davide Zilli, Tomasz Rudny and Alessandra Tosi.

Automatic Type Inference with a Nested Latent Variable Model Paper

64 Carlos Vieira, Adelson Araújo Júnior, Deângela C. G. Neves and Leonardo C. T. Bezerra.

iSklearn: Assessing irace for automated machine learning

20 José Miguel Hernández-Lobato, Daniel Hernández-Lobato, Michael A. Gelbart, Brandon Reagen, Rob Adolf, Paul N. Whatmough, David Brooks and Gu-Yeon Wei.

A Comparison of Several Models on Hardware Accelerator Data for Deep Neural Networks Design using Bayesian Optimization Paper

21 Jungtaek Kim and Seungjin Choi.

Automated Machine Learning for Soft Voting in an Ensemble of Tree-based Classifiers Paper

30 Rauf Izmailov, Peter Lin and Chumki Basu.

Automatic Feature Selection in Learning Using Privileged Information Paper

31 Man-Ling Sung, Jan Silovsky, Man-Hung Siu, Herbert Gish and Chinnu Pittapally.

Neural Network Conversion of Machine Learning Pipelines Paper

33 Maximilian Alber, Irwan Bello, Barret Zoph, Pieter-Jan Kindermans, Prajit Ramachandran and Quoc Le.

Backprop Evolution Paper

59 Wenyi Wang and William Welch.

Bayesian Optimization Exploiting Monotonicity and Its Application in Machine Learning Hyperparameter Tuning Paper

63 Patricio Cerda, Gaël Varoquaux and Balázs Kégl.

Similarity encoding for learning with dirty categorical data Paper

23 Eduardo Garrido-Merchán and Daniel Hernández-Lobato.

Dealing with Categorical and Integer-valued Variables in Bayesian Optimization with Gaussian Processes Paper

38 Marcel Wever, Felix Mohr and Eyke Hüllermeier.

ML-Plan for Unlimited-Length Machine Learning Pipelines Paper

15 Herilalaina Rakotoarison and Michèle Sebag. Paper

AutoML with Monte Carlo Tree Search

39 Luca Franceschi, Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo and Paolo Frasconi.

Demo Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning Paper

48 Maria João Ferreira and Pavel Brazdil.

Workflow Recommendation for Text Classification with Active Testing Method Paper

58 Udayan Khurana, Horst Samulowitz and Deepak Turaga. Paper

Ensembles with Automated Feature Engineering