ICML

Sparse Representation Classification via Screening for Graphs

Cencheng Shen, Li Chen, Yuexiao Dong, Carey Priebe

Comments Accepted at Learning and Reasoning with Graph-Structured Representations in International Conference on Machine Learning (ICML) 2019

Towards Task and Architecture-Independent Generalization Gap Predictors

Scott Yak, Javier Gonzalvo, Hanna Mazzawi

Comments 8 pages, 6 figures, 2 tables. To be presented at ICML 2019 "Understanding and Improving Generalization in Deep Learning" Workshop (poster)

Bayesian Optimization of Composite Functions

Raul Astudillo, Peter I. Frazier

Comments In Proceedings of the 36th International Conference on Machine Learning, PMLR 97:354-363, 2019

Journal ref In Proceedings of the 36th International Conference on Machine Learning, PMLR 97:354-363, 2019

A Fast-Optimal Guaranteed Algorithm For Learning Sub-Interval Relationships in Time Series

Saurabh Agrawal, Saurabh Verma, Anuj Karpatne, Stefan Liess, Snigdhansu Chatterjee, Vipin Kumar

Comments Accepted at The Thirty-sixth International Conference on Machine Learning (ICML 2019), Time Series Workshop. arXiv admin note: substantial text overlap with arXiv:1802.06095

Knowledge-augmented Column Networks: Guiding Deep Learning with Advice

Mayukh Das, Devendra Singh Dhami, Yang Yu, Gautam Kunapuli, Sriraam Natarajan

Comments Presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA. arXiv admin note: substantial text overlap with arXiv:1904.06950

Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)

Gregory Plumb, Maruan Al-Shedivat, Eric Xing, Ameet Talwalkar

Comments presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA. arXiv admin note: substantial text overlap with arXiv:1902.06787

A Case for Backward Compatibility for Human-AI Teams

Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, Eric Horvitz

Comments presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA

Y-GAN: A Generative Adversarial Network for Depthmap Estimation from Multi-camera Stereo Images

Miguel Alonso

Comments Accepted for Presentation at the ICML 2019 LatinX in AI Research Workshop

Concept Tree: High-Level Representation of Variables for More Interpretable Surrogate Decision Trees

Xavier Renard, Nicolas Woloszko, Jonathan Aigrain, Marcin Detyniecki

Comments presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA

Graduated Optimization of Black-Box Functions

Weijia Shao, Christian Geißler, Fikret Sivrikaya

Comments Accepted Workshop Submission for the 6th ICML Workshop on Automated Machine Learning

Breaking Inter-Layer Co-Adaptation by Classifier Anonymization

Ikuro Sato, Kohta Ishikawa, Guoqing Liu, Masayuki Tanaka

Comments 9 pages. Accepted to ICML 2019

A Perspective on Objects and Systematic Generalization in Model-Based RL

Sjoerd van Steenkiste, Klaus Greff, Jürgen Schmidhuber

Comments Accepted to the ICML 2019 workshop on Workshop on Generative Modeling and Model-Based Reasoning for Robotics and AI

A Theory of Regularized Markov Decision Processes

Matthieu Geist, Bruno Scherrer, Olivier Pietquin

Comments ICML 2019

Towards Interactive Training of Non-Player Characters in Video Games

Igor Borovikov, Jesse Harder, Michael Sadovsky, Ahmad Beirami

Comments presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA

An Empirical Study on Hyperparameters and their Interdependence for RL Generalization

Xingyou Song, Yilun Du, Jacob Jackson

Comments Published in ICML 2019 Workshop "Understanding and Improving Generalization in Deep Learning"

The Principle of Unchanged Optimality in Reinforcement Learning Generalization

Alex Irpan, Xingyou Song

Comments Published at ICML 2019 Workshop "Understanding and Improving Generalization in Deep Learning"

Biomedical Named Entity Recognition via Reference-Set Augmented Bootstrapping

Joel Mathew, Shobeir Fakhraei, José Luis Ambite

Comments 5 pages, 1 Figure, 2 Table, ICML 2019 Workshop on Computational Biology

Super-resolution of Time-series Labels for Bootstrapped Event Detection

Ivan Kiskin, Udeepa Meepegama, Steven Roberts

Comments Accepted at the Time-series workshop at ICML 2019, Long Beach

Bayesian Deconditional Kernel Mean Embeddings

Kelvin Hsu, Fabio Ramos

Comments In the Proceedings of the 36th International Conference on Machine Learning (ICML 2019), Long Beach, California, USA

Are Graph Neural Networks Miscalibrated?

Leonardo Teixeira, Brian Jalaian, Bruno Ribeiro

Comments Presented at the ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data

Optimality Implies Kernel Sum Classifiers are Statistically Efficient

Raphael Arkady Meyer, Jean Honorio

Journal ref International Conference on Machine Learning (ICML) 2019

Implicit Generative Modeling of Random Noise during Training for Adversarial Robustness

Priyadarshini Panda, Kaushik Roy

Comments Preliminary version of this work accepted at ICML 2019 (Workshop on Uncertainty and Robustness in Deep Learning)

Explainability Techniques for Graph Convolutional Networks

Federico Baldassarre, Hossein Azizpour

Comments Accepted at the ICML 2019 Workshop "Learning and Reasoning with Graph-Structured Representations" (poster + spotlight talk)

Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation

Sahil Singla, Eric Wallace, Shi Feng, Soheil Feizi

Comments Proceedings of the 36th International Conference on Machine Learning, 2019

Anomaly Detection With Multiple-Hypotheses Predictions

Duc Tam Nguyen, Zhongyu Lou, Michael Klar, Thomas Brox

Comments In proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, California, PMLR 97, 2019

Scalable Learning in Reproducing Kernel Krein Spaces

Dino Oglic, Thomas Gärtner

Comments The version accepted for presentation at ICML 2019

On the Spectral Bias of Neural Networks

Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred A. Hamprecht, Yoshua Bengio, Aaron Courville

Comments 23 pages

Journal ref ICML 2019

An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method

Li Shen, Peng Sun, Yitong Wang, Wei Liu, Tong Zhang

Comments Accepted by ICML 2018

On Matching Pursuit and Coordinate Descent

Francesco Locatello, Anant Raj, Sai Praneeth Karimireddy, Gunnar Rätsch, Bernhard Schölkopf, Sebastian U. Stich, Martin Jaggi

Journal ref ICML 2018 - Proceedings of the 35th International Conference on Machine Learning

Unsupervised pre-training helps to conserve views from input distribution

Nicolas Pinchaud

Comments ICML 2012 workshop