ICML

Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training

Xi Wu, Uyeong Jang, Jiefeng Chen, Lingjiao Chen, Somesh Jha

Comments To appear in ICML 2018

Yes, but Did It Work?: Evaluating Variational Inference

Yuling Yao, Aki Vehtari, Daniel Simpson, Andrew Gelman

Comments Appearing at International Conference on Machine Learning 2018

Journal ref Proceedings of the 35th International Conference on Machine Learning, PMLR 80:5581-5590, 2018. http://proceedings.mlr.press/v80/yao18a.html

Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering

Pan Li, Olgica Milenkovic

Comments A short version of this paper is presented in ICML 2018. This version includes the definition of a sequence of eigenvalues for 1-Laplacian

Bayesian Optimization of Combinatorial Structures

Ricardo Baptista, Matthias Poloczek

Comments Published at International Conference on Machine Learning 2018

TherML: Thermodynamics of Machine Learning

Alexander A. Alemi, Ian Fischer

Comments Presented at the ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models

Contextual Multi-Armed Bandits for Causal Marketing

Neela Sawant, Chitti Babu Namballa, Narayanan Sadagopan, Houssam Nassif

Journal ref Sawant N, Namballa CB, Sadagopan N, and Nassif H. Contextual Multi-Armed Bandits for Causal Marketing. International Conference on Machine Learning (ICML'18) Workshops, Stockholm, Sweden, 2018

Diversifying Music Recommendations

Houssam Nassif, Kemal Oral Cansizlar, Mitchell Goodman, SVN Vishwanathan

Comments Machine Learning for Music Discovery Workshop at the 33rd International Conference on Machine Learning (ICML'16), New York, 2016

High Performance Zero-Memory Overhead Direct Convolutions

Jiyuan Zhang, Franz Franchetti, Tze Meng Low

Comments the 35th International Conference on Machine Learning(ICML 2018), camera ready

Local Density Estimation in High Dimensions

Xian Wu, Moses Charikar, Vishnu Natchu

Comments Preliminary version appeared in ICML 2018

GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms

Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer

Comments accepted at ICML 2018, 14 pages

Bounding and Counting Linear Regions of Deep Neural Networks

Thiago Serra, Christian Tjandraatmadja, Srikumar Ramalingam

Comments ICML 2018

User preferences in Bayesian multi-objective optimization: the expected weighted hypervolume improvement criterion

Paul Feliot, Julien Bect, Emmanuel Vazquez

Comments To be published in the proceedings of LOD 2018 -- The Fourth International Conference on Machine Learning, Optimization, and Data Science -- September 13-16, 2018 -- Volterra, Tuscany, Italy

Beyond $1/2$-Approximation for Submodular Maximization on Massive Data Streams

Ashkan Norouzi-Fard, Jakub Tarnawski, Slobodan Mitrović, Amir Zandieh, Aida Mousavifar, Ola Svensson

Journal ref Proc. of 35th International Conference on Machine Learning (ICML), 2018, pages 3829-3838

Candidates vs. Noises Estimation for Large Multi-Class Classification Problem

Lei Han, Yiheng Huang, Tong Zhang

Comments Published in ICML 2018

Learning Deep Mixtures of Gaussian Process Experts Using Sum-Product Networks

Martin Trapp, Robert Peharz, Carl E. Rasmussen, Franz Pernkopf

Comments Presented at the Workshop on Tractable Probabilistic Models (TPM 2018), ICML 2018

Visualizing and Understanding Atari Agents

Sam Greydanus, Anurag Koul, Jonathan Dodge, Alan Fern

Comments ICML 2018 conference paper. Code: https://github.com/greydanus/visualize_atari Blog: https://greydanus.github.io/2017/11/01/visualize-atari/

Learning Independent Causal Mechanisms

Giambattista Parascandolo, Niki Kilbertus, Mateo Rojas-Carulla, Bernhard Schölkopf

Comments ICML 2018

Journal ref Proceedings of the 35th International Conference on Machine Learning, PMLR 80:4036-4044, 2018

Community Regularization of Visually-Grounded Dialog

Akshat Agarwal, Swaminathan Gurumurthy, Vasu Sharma, Mike Lewis, Katia Sycara

Comments 7 pages, ICML/AAMAS Adaptive Learning Agents Workshop 2018 and CVPR Visual Dialog Workshop 2018. Code available at https://github.com/agakshat/visualdialog-pytorch

Blind Justice: Fairness with Encrypted Sensitive Attributes

Niki Kilbertus, Adrià Gascón, Matt J. Kusner, Michael Veale, Krishna P. Gummadi, Adrian Weller

Comments published at ICML 2018

Journal ref Proceedings of the 35th International Conference on Machine Learning, PMLR 80:2630-2639, 2018

Latent Space Policies for Hierarchical Reinforcement Learning

Tuomas Haarnoja, Kristian Hartikainen, Pieter Abbeel, Sergey Levine

Comments ICML 2018; Videos: https://sites.google.com/view/latent-space-deep-rl Code: https://github.com/haarnoja/sac

Graph Capsule Convolutional Neural Networks

Saurabh Verma, Zhi-Li Zhang

Comments Accepted at Joint ICML and IJCAI Workshop on Computational Biology, Stockholm, Sweden, 2018

Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference

Louis C. Tiao, Edwin V. Bonilla, Fabio Ramos

Comments Presented at the ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models. Stockholm, Sweden, 2018

A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming

Alp Yurtsever, Olivier Fercoq, Francesco Locatello, Volkan Cevher

Comments Appears in Proceedings of the 35th International Conference on Machine Learning (ICML 2018)

Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks

Minmin Chen, Jeffrey Pennington, Samuel S. Schoenholz

Comments ICML 2018 Conference Proceedings

MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels

Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, Li Fei-Fei

Journal ref published at ICML 2018

Analyzing Uncertainty in Neural Machine Translation

Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato

Comments ICML 2018

TACO: Learning Task Decomposition via Temporal Alignment for Control

Kyriacos Shiarlis, Markus Wulfmeier, Sasha Salter, Shimon Whiteson, Ingmar Posner

Comments 12 Pages. Published at ICML 2018

Policy Optimization as Wasserstein Gradient Flows

Ruiyi Zhang, Changyou Chen, Chunyuan Li, Lawrence Carin

Comments Accepted by ICML 2018; Initial version on Deep Reinforcement Learning Symposium at NIPS 2017

Delayed Impact of Fair Machine Learning

Lydia T. Liu, Sarah Dean, Esther Rolf, Max Simchowitz, Moritz Hardt

Comments 37 pages, 6 figures

Journal ref Proceedings of the 35th International Conference on Machine Learning, PMLR 80:3150-3158, 2018

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, Sergey Levine

Comments ICML 2018 Videos: sites.google.com/view/soft-actor-critic Code: github.com/haarnoja/sac