ICML

Hierarchical Clustering with Structural Constraints

Vaggos Chatziafratis, Rad Niazadeh, Moses Charikar

Comments In Proc. 35th International Conference on Machine Learning (ICML 2018)

Multi-task Maximum Entropy Inverse Reinforcement Learning

Adam Gleave, Oliver Habryka

Comments Presented at 1st Workshop on Goal Specifications for Reinforcement Learning (ICML/IJCAI/AAMAS 2018)

Bayesian Uncertainty Estimation for Batch Normalized Deep Networks

Mattias Teye, Hossein Azizpour, Kevin Smith

Comments ICML 2018

Tune: A Research Platform for Distributed Model Selection and Training

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

Comments 8 Pages, Presented at the 2018 ICML AutoML workshop

Exploring Hierarchy-Aware Inverse Reinforcement Learning

Chris Cundy, Daniel Filan

Comments Presented at the first Workshop on Goal Specifications for Reinforcement Learning, ICML 2018, Stockholm, Sweden

Journal ref 1st Workshop on Goal Specifications for Reinforcement Learning, ICML 2018, Stockholm, Sweden, 2018

GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks

Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, Andrew Rabinovich

Comments ICML 2018

Journal ref Proceedings of the 35th International Conference on Machine Learning (2018), 793-802

Automatic Gradient Boosting

Janek Thomas, Stefan Coors, Bernd Bischl

Comments 6 pages, 1 figure, ICML 2018 AutoML Workshop

Noisin: Unbiased Regularization for Recurrent Neural Networks

Adji B. Dieng, Rajesh Ranganath, Jaan Altosaar, David M. Blei

Comments In Proceedings of the International Conference on Machine Learning, 2018

Explorations in Homeomorphic Variational Auto-Encoding

Luca Falorsi, Pim de Haan, Tim R. Davidson, Nicola De Cao, Maurice Weiler, Patrick Forré, Taco S. Cohen

Comments 16 pages, 8 figures, ICML workshop on Theoretical Foundations and Applications of Deep Generative Models

Measuring abstract reasoning in neural networks

David G. T. Barrett, Felix Hill, Adam Santoro, Ari S. Morcos, Timothy Lillicrap

Comments ICML 2018

VFunc: a Deep Generative Model for Functions

Philip Bachman, Riashat Islam, Alessandro Sordoni, Zafarali Ahmed

Comments To be presented at the ICML 2018 workshop on Prediction and Generative Modeling in Reinforcement Learning

Geometric Generalization Based Zero-Shot Learning Dataset Infinite World: Simple Yet Powerful

Rajesh Chidambaram, Michael Kampffmeyer, Willie Neiswanger, Xiaodan Liang, Thomas Lachmann, Eric Xing

Journal ref ICML 2018, Workshop TADGM

Maximally Invariant Data Perturbation as Explanation

Satoshi Hara, Kouichi Ikeno, Tasuku Soma, Takanori Maehara

Comments presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden

Black-box Adversarial Attacks with Limited Queries and Information

Andrew Ilyas, Logan Engstrom, Anish Athalye, Jessy Lin

Comments ICML 2018. This supercedes the previous paper "Query-efficient Black-box adversarial examples."

Tempered Adversarial Networks

Mehdi S. M. Sajjadi, Giambattista Parascandolo, Arash Mehrjou, Bernhard Schölkopf

Comments accepted to ICML 2018

Is Q-learning Provably Efficient?

Chi Jin, Zeyuan Allen-Zhu, Sebastien Bubeck, Michael I. Jordan

Comments Best paper in ICML 2018 workshop "Exploration in RL"

Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters

Aniruddh Raghu, Omer Gottesman, Yao Liu, Matthieu Komorowski, Aldo Faisal, Finale Doshi-Velez, Emma Brunskill

Comments Accepted to workshop on Machine Learning for Causal Inference, Counterfactual Prediction, and Autonomous Action at ICML 2018

Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks

Lechao Xiao, Yasaman Bahri, Jascha Sohl-Dickstein, Samuel S. Schoenholz, Jeffrey Pennington

Comments ICML 2018 Conference Proceedings

Asymmetric Variational Autoencoders

Guoqing Zheng, Yiming Yang, Jaime Carbonell

Comments ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models

XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings

Amélie Royer, Konstantinos Bousmalis, Stephan Gouws, Fred Bertsch, Inbar Mosseri, Forrester Cole, Kevin Murphy

Comments Domain Adaptation for Visual Understanding at ICML'18

Convolutional Normalizing Flows

Guoqing Zheng, Yiming Yang, Jaime Carbonell

Comments ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models

Neural Machine Translation for Query Construction and Composition

Tommaso Soru, Edgard Marx, André Valdestilhas, Diego Esteves, Diego Moussallem, Gustavo Publio

Comments ICML workshop on Neural Abstract Machines & Program Induction v2 (NAMPI), extended abstract

Asynchronous Byzantine Machine Learning (the case of SGD)

Georgios Damaskinos, El Mahdi El Mhamdi, Rachid Guerraoui, Rhicheek Patra, Mahsa Taziki

Comments accepted to ICML 2018

NAPS: Natural Program Synthesis Dataset

Maksym Zavershynskyi, Alex Skidanov, Illia Polosukhin

Comments 4 pages, 5 tables in 2nd Workshop on Neural Abstract Machines & Program Induction (NAMPI), @ICML 2018

Deep Learning for Singing Processing: Achievements, Challenges and Impact on Singers and Listeners

Emilia Gómez, Merlijn Blaauw, Jordi Bonada, Pritish Chandna, Helena Cuesta

Comments Keynote speech, 2018 Joint Workshop on Machine Learning for Music. The Federated Artificial Intelligence Meeting (FAIM), a joint workshop program of ICML, IJCAI/ECAI, and AAMAS

Robust Learning of Trimmed Estimators via Manifold Sampling

Matt Menickelly, Stefan M. Wild

Comments In ICML 2018 Workshop on Modern Trends in Nonconvex Optimization for Machine Learning

Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions

Shuaiwen Wang, Wenda Zhou, Haihao Lu, Arian Maleki, Vahab Mirrokni

Comments The paper is published on ICML 2018

Video Prediction with Appearance and Motion Conditions

Yunseok Jang, Gunhee Kim, Yale Song

Comments Accepted paper at ICML 2018. Project page: http://vision.snu.ac.kr/projects/amc-gan

Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry

Maximilian Nickel, Douwe Kiela

Comments Accepted at ICML'18

Functional Gradient Boosting based on Residual Network Perception

Atsushi Nitanda, Taiji Suzuki

Comments 22 pages, 1 figure, 1 table. An extended version of ICML 2018 paper