-
8:35am • John Shawe-Taylor, Sparsity Based Bounds on Learners and their Applications
-
9:20am • Yuxin Chen, Sequential Information Maximization: When is Greedy Near-optimal?
-
9:40am • Assaf Hallak, Off-policy Model-based Learning under Unknown Factored Dynamics
-
10:30am • Kveton Branislav, Learning to Act Greedily: Matroid and Polymatroid Bandits
-
11:15am • Aurelien Bellet, The Frank-Wolfe Algorithm: Recent Results and Applications to High-Dimensional Similarity Learning and Distributed Optimization
-
2:00pm • Ke Wei, Conjugate Gradient Iterative Hard Thresholding for Compressed Sensing and Matrix Completion
-
2:45pm • Guy Lever, Greedy Function Approximation for Efficient Non-Parametric Approaches to Reinforcement Learning
-
3:30pm • Alexandre Drouin, Greedy Biomarker Discovery in the Genome with Applications to Antimicrobial Resistance
-
3:50pm • poster sessions
-
4:30pm • Yash Sastangi, Exploiting Submodular Value Functions for Faster Dynamic Sensor Selection
-
4:50pm • Cedric Herzet, Beyond Uniform Analysis: Exploiting the Decay of Sparse Vectors
-
8:35am • Mihaela van der Schaar, UCLA, One Teacher for Every Student: Personalizing Education
-
9:00am • Andrew Lan, Rice University, Modeling Student Responses Using the Dealbreaker Model
-
9:25am • Thorsten Joachims, Cornell University, Learning Representations of Student Knowledge and Educational Content
-
9:50am • Mehdi Sajjadi, University of Hamburg, Peer Grading in a Course on Algorithms and Data Structures: Machine Learning Algorithms do not Improve over Simple Baselines
-
10:30am • Mykola Pechenizkiy, Eindhoven University of Technology, Grand challenges in Educational Data Mining
-
10:55am • Jerry Zhu, University of Wisconsin Madison, Machine Teaching
-
11:20am • Piyush Rai, Duke University, Scalable Bayesian Latent Factor Models for Binary Matrices and Tensors
-
11:45am • Zoran Popovic, University of Washington, Generative Optimization of the Learning Ecosystem
-
1:50pm • Poster Spotlight
-
2:00pm • Poster Session
-
2:30pm • Mehran Sahami, Stanford University, Statistical Modeling to Understand the Dynamics of Student Populations
-
2:55pm • Igor Labutov, Cornell University, Curriculum Mining: Towards Connecting Resources that Explain
-
3:20pm • Burr Settles, Duolingo, Machine Learning for Spaced Repetition and Variable Rewards
-
3:45pm • Jacob Whitehill, HarvardX, Automatic Recognition of Student (Dis)engagement
-
4:30pm • Alina von Davier, ETS, Virtual & Collaborative Assessments: Examples, Implications and Challenges for Educational Measurement
-
4:55pm • Joseph Jay Williams, HarvardX, MOOClets: An Abstraction and API for Machine Learning Research to Optimize and Personalize Users‚Äô Interactions with Large-scale Online Technologies
-
5:20pm • Chris Piech, Stanford University, Deep Knowledge Tracing
-
5:45pm • General discussion and closing remarks
-
8:30am • Coffee and Welcome
-
8:50am • Thomas G. Diettrerich, Efficient Sampling for Simulator-Defined MDPs
-
10:30am • Matteus Tanha, Tse-Han Huang, Geoffrey J. Gordon and David J. Yaron, Imitation Learning for Accelerating Iterative Computation of Fixed Points
-
10:50am • Matteo Pirotta and Marcello Restelli, On the Minimization of the Policy Gradient in Inverse Reinforcement Learning
-
11:10am • Philip Bachman and Doina Precup, Learning Policies for Data Imputation with Guided Policy Search
-
11:30am • Herke Van Hoof, Jan Peters and Gerhard Neumann, Non-Parametric Policy Learning for High-Dimensional State Representations
-
2:00pm • Invited Talk. Marcus Hutter
-
3:00pm • Jan Leike and Marcus Hutter, On the Optimality of General Reinforcement Learners
-
3:20pm • Ashique Rupam Mahmood, Huizhen Yu, Martha White and Richard Sutton, Emphatic Temporal-Difference Learning
-
3:40pm • Ludovic Denoyer and Patrick Gallinari, Deep Sequential Neural Networks
-
4:00pm • Poster session.
-
5:00pm • Invited Talk. Shie Mannor
-
9:00am • Intro
-
9:10am • Manik Varma, Extreme Classification: A New Paradigm for Ranking & Recommendation
-
10:30am • Jason Weston, Hashtags, Clicks and Likes: Supervision for Content-based Posts
-
11:20am • Locally Non-linear Embeddings for Extreme Multi-Label Learning (Kush Bhatia, Himanshu Jain, Purushottam Kar, Prateek Jain and Manik Varma)
-
11:40am • Consistent Label Tree Classifiers for Extreme Multi-Label Classification (Kalina Jasinska and Krzysztof Dembczynski)
-
2:00pm • John Langford, The Elusive Theory of Efficient Classification
-
2:50pm • Rademacher Complexity Margin Bounds for Learning with a Large Number of Classes (Vitaly Kuznetsov, Mehryar Mohri and Umar Syed)
-
3:10pm • Sequential Dynamic Classification for Large Scale Multiclass Problems (Raphael Puget, Nicolas Baskiotis and Patrick Gallinari)
-
3:30pm • Large-scale Bayesian Multi-label Learning via Positive Labels Only (Piyush Rai, Changwei Hu, Ricardo Henao and Lawrence Carin)
-
4:30pm • Jia Deng, Knowledge-Driven Recognition of Objects and Actions
-
5:20pm • Label Filters for Large Scale Multilabel Classification (Alexandru Niculescu-Mizil and Ehsan Abbasnejad)
-
5:40pm • Wrap-up
-
9:00am • Introduction
-
9:10am • Nick Diakopoulos Algorithmic Accountability and Transparency in Journalism
-
10:30am • Sara Hajian Discrimination- and Privacy-Aware Data Mining
-
11:10am • Salvatore Ruggieri Privacy Attacks and Anonymization Methods as Tools for Discrimination Discovery and Fairness
-
11:50am • Toshihiro Kamishima and Kazuto Fukuchi Future Directions of Fairness-Aware Data Mining: Recommendation, Causality, and Theoretical Aspects
-
2:00pm • Muhammad Bilal Zafar, Isabel Valera Martinez, Manuel Gomez Rodriguez, and Krishna Gummadi Fairness Constraints: A Mechanism for Fair Classification
-
2:30pm • Benjamin Fish, Jeremy Kun, and Adam D. Lelkes Fair Boosting: A Case Study
-
3:00pm • Zubin Jelveh and Michael Luca Towards Diagnosing Accuracy Loss in Discrimination-Aware Classification: An Application to Predictive Policing
-
3:30pm • Indre Zliobaite On the Relation between Accuracy and Fairness in Binary Classification
-
4:30pm • Fernando Diaz, Sorelle Friedler, Mykola Pechenizkiy, Hanna Wallach, and Suresh Venkatasubramanian (Moderator) A Closing Panel Discussion
-
8:45am • Introduction
-
8:55am • Kristian Kersting, Poisson Dependency Networks: Gradient Boosted Models for Multivariate Count Data
-
9:40am • Short papers spotlights
-
10:30am • Joelle Pineau, Analyzing Open Data from the City of Montreal
-
10:55am • Lidia Contreras Ochando, Airvlc: An application for realFtime forecasting urban air pollution
-
11:10am • Albrecht Zimmermann, Profiling users of the Velo'v bike sharing system
-
11:25am • Nikolas Zygouras, Towards detection of faulty traffic sensors in real-time
-
11:40am • Indre Zliobaite, Accessibility by public transport predicts residential real estate prices: a case study in Helsinki region
-
11:55am • Thomas Liebig, Distributed Traffic Flow Prediction with Label Proportions
-
2:00pm • Eleni Pratsini, Using Big Mobile Data to Analyze Social Events in Cities
-
2:45pm • Axel Schulz, Event-based Clustering for Reducing Labeling Costs of Incident-Related Microposts
-
3:00pm • Boris Chidlovskii, Improved Trip Planning by Learning from Travelers' Choices
-
3:15pm • Stefan Funke, Automatic Extrapolation of MissF ing Road Network Data in OpenStreetMap
-
3:30pm • Short papers spotlights
-
4:30pm • Sharad Mehrotra, Towards 'on the fly' data cleaning
-
9:20am • Introductory Remarks
-
9:30am • Brian McFee, NYU, The Role of Structure Analysis in Music Discovery
-
10:30am • Philippe Hamel, Google, To Have a Tiger by the Tail: Improving Music Recommendation for International Users
-
11:00am • Arthur Flexer, Austrian Research Institute for Artificial Intelligence, The Impact of Hubness on Music Recommendation
-
11:30am • Sander Dieleman, Ghent University, Deep Content-Based Music Recommendation
-
12:00pm • Bob L. Sturm, Queen Mary University of London, The Scientific Evaluation of Music Content Analysis Systems: Valid Empirical Foundations for Future Real-World Impact
-
2:00pm • Geoffroy Peeters, IRCAM, When Audio Features Reach Machine Learning
-
2:30pm • Matthew Prockup, Drexel University, Pandora Media, Modeling Rhythmic Attributes in Music At Scale with Tree Ensembles and the Music Genome Project
-
2:50pm • Dawen Liang, Columbia University, Content-Aware Collaborative Music Recommendation Using Pre-trained Neural Networks
-
3:10pm • Thomas Wilmering, Queen Mary University of London, Towards High Level Feature Extraction from Large Live Music Recording Archives
-
4:30pm • Cedric Mesnage, University of Bristol, Trend Extraction on Twitter Time Series for Music Discovery
-
4:50pm • Keunwoo Choi, Queen Mary University of London, Understanding Music Playlists
-
5:10pm • Bea Vad, University of Glasgow, Exploring Music with a Probabilistic Projection Interface
-
8:45am • Open
-
9:00am • Julien Demouth, NVIDIA
-
9:15am • Ben Glocker, Imperial College London, Semantic Imaging: Learning to Understand Medical Images
-
10:30am • Alexander Loktyushin, Retrospective motion correction of magnitude-input MR images
-
10:45am • Amir Alansary, Automatic brain localisation in foetal MRI using superpixel graphs
-
11:00am • Bertrand Thirion, INRIA, Learning representations from functional brain images
-
11:45am • Orhan Firat, Learning Deep Temporal Representations for fMRI Brain Decoding
-
12:00pm • Marco Lorenzi, Modelling Non-Stationary and Non-Separable Spatio-Temporal Changes in Neurodegeneration via Gaussian Process Convolution
-
12:15pm • Jonathan Young, Improving MRI brain image classification with anatomical regional kernels
-
2:30pm • John Ashburner, UCL, Applying pattern recognition to anatomical scans
-
3:15pm • Claudio Stamile, A Graph Based Classification Method for Multiple Sclerosis Clinical Form Using Support Vector Machine
-
3:30pm • Mahsa Shakeri, Classification of Alzheimer's Disease using Discriminant Manifolds of Hippocampus Shapes
-
3:45pm • Rahaf Aljundi, Transfer Learning for Prostate Cancer Mapping Based on Multicentric MR imaging databases
-
4:30pm • Marleen de Bruijne, Erasmus Medical Center & DIKU Copenhagen
-
5:15pm • Annegreet van Opbroek, Feature-Space Transformation Improves Supervised Segmentation Across Scanners
-
5:30pm • Gerard Sanroma, Discriminative Dimensionality Reduction for Patch-based Label Fusion
-
5:45pm • Closing + best paper award
-
8:30am • Tutorial. Marc Bellemare, The Atari Learning Environment
-
9:00am • Invited Talk. David Silver
-
10:30am • Orly Avner and Shie Mannor, Learning to coordinate without communication in multi-user multi-armed bandit problems
-
10:50am • Aristide Tossou and Christos Dimitrakakis, Differentially private multi-agent multi-armed bandits
-
11:10am • Yahel David and Nahum Shimkin, PAC Algorithms for the Infinitely-Many Armed Problem with Multiple Pools
-
11:30am • Gergely Neu, Explore no more: Simple and tight high-probability bounds for non-stochastic bandits
-
2:00pm • Invited Talk. Lihong Li
-
3:00pm • Aviv Tamar, Yinlam Chow, Mohammad Ghavamzadeh and Shie Mannor, Policy Gradient for Coherent Risk Measures
-
3:20pm • Diederik Roijers, Shimon Whiteson, Peter Vamplew and Richard Dazeley, Why Multi-objective Reinforcement Learning?
-
3:40pm • Christian Wirth and Gerhard Neumann, Model-Free Preference-based Reinforcement Learning
-
4:00pm • Poster Session
-
5:00pm • Invited Talk. Csaba Szepesvari
-
8:45am • Welcome and Opening Remarks
-
8:55am • Juergen Schmidhuber, PowerPlay: training an increasingly general (reinforcement learning) problem solver by continually searching for the simplest still unsolvable problem
-
9:45am • Imitation Learning Applied to Embodied Conversational Agent, Bilal Piot, Olivier Pietquin and Matthieu Geist
-
10:30am • Efficient Real-Time Pixelwise Object Class Labeling for Safe Human-Robot Collaboration in Industrial Domain, Vivek Sharma, Frank Dittrich, Sule Yildirim-Yayilgan and Luc Van Gool
-
10:45am • Human-Guided Learning of Social Action Selection for Robot-Assisted Therapy, Emmanuel Senft, Paul Baxter and Tony Belpaeme
-
11:00am • Teaching iCub to recognize objects using deep Convolutional Neural Networks, Giulia Pasquale, Carlo Ciliberto, Francesca Odone, Lorenzo Rosasco and Lorenzo Natale
-
11:15am • Ruslan Salakhutdinov, Learning Recurrent Attention Models
-
12:05pm • Discussion session 1
-
2:00pm • Bjorn Schuller, Less Input: Cooperative Learning for Emotionally Intelligent Systems
-
2:50pm • Latent Goal Analysis for Dimension Reduction in Reinforcement Learning, Matthias Rolf and Minoru Asada
-
3:05pm • Online Mean Field Approximation for Automated Experimentation, Shaona Ghosh and Adam Prugel-Bennett
-
3:20pm • Iterative Embedding with Robust Correction using Feedback of Error Observed, Praneeth Vepakomma and Ahmed Elgammal
-
3:35pm • A Coactive Learning Perspective on Interactive Machine Translation, Artem Sokolov, Shay Cohen and Stefan Riezler
-
3:50pm • Visualizing User Model in Exploratory Search Tasks, Kalle Ilves, Alan Medlar and Dorota Glowacka
-
4:30pm • Ashutosh Saxena and Ashesh Jain, RoboBrain Knowledge Engine: Learning from Weak Human Signals
-
5:20pm • Discussion session 2
-
9:10am • Matthew Hoffmann (Cambridge), Bandits and Bayesian optimization for AutoML
-
9:50am • Poster Spotlights
-
10:30am • Michele Sebag (CNRS), Algorithm Recommendation as Collaborative Filtering
-
11:10am • Poster spotlights
-
11:30am • 1st Poster Session
-
2:00pm • Juergen Schmidhuber (IDSIA), Recursive Self-Improvement
-
2:40pm • David Duvenaud (Harvard), Automatically constructing models, and automatically explaining them, too.
-
3:20pm • 2nd Poster Session
-
4:30pm • Joaquin Vanschoren (Eindhoven Univ. of Tech.), OpenML: A Foundation for Networked & Automatic Machine Learning
-
5:10pm • Marc Boulle (Orange), AutoML Challenge
-
5:30pm • Panel Discussion: Marc Boulle, Rich Caruana, David Duvenaud, Matthew Hoffmann, Juergen Schmidhuber, Michele Sebag, Joaquin Vanschoren.