ICML

Convolutional Kernel Networks for Graph-Structured Data

Dexiong Chen, Laurent Jacob, Julien Mairal

Journal ref International Conference on Machine Learning (ICML), Jul 2020

Learning Near Optimal Policies with Low Inherent Bellman Error

Andrea Zanette, Alessandro Lazaric, Mykel Kochenderfer, Emma Brunskill

Comments Bug fixes in appendix; appears in ICML 2020

Reliable Fidelity and Diversity Metrics for Generative Models

Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi, Jaejun Yoo

Comments First two authors have contributed equally; ICML 2020 accepted

It's Not What Machines Can Learn, It's What We Cannot Teach

Gal Yehuda, Moshe Gabel, Assaf Schuster

Comments Accepted to ICML 2020

Being Bayesian about Categorical Probability

Taejong Joo, Uijung Chung, Min-Gwan Seo

Comments ICML 2020

Symbolic Network: Generalized Neural Policies for Relational MDPs

Sankalp Garg, Aniket Bajpai, Mausam

Comments In Proceeding of ICML 2020. Code can be found at https://github.com/dair-iitd/symnet

On Layer Normalization in the Transformer Architecture

Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, Tie-Yan Liu

Journal ref Published on ICML 2020

Self-supervised Label Augmentation via Input Transformations

Hankook Lee, Sung Ju Hwang, Jinwoo Shin

Comments Accepted to ICML 2020. Code available at https://github.com/hankook/SLA

Student Specialization in Deep ReLU Networks With Finite Width and Input Dimension

Yuandong Tian

Comments Accepted in ICML 2020

Single Point Transductive Prediction

Nilesh Tripuraneni, Lester Mackey

Comments 37th International Conference on Machine Learning (ICML 2020)

Convolutional dictionary learning based auto-encoders for natural exponential-family distributions

Bahareh Tolooshams, Andrew H. Song, Simona Temereanca, Demba Ba

Journal ref International Conference on Machine Learning (ICML) 2020

Learning Optimal Tree Models Under Beam Search

Jingwei Zhuo, Ziru Xu, Wei Dai, Han Zhu, Han Li, Jian Xu, Kun Gai

Comments To appear in the 37th International Conference on Machine Learning (ICML 2020)

On the Number of Linear Regions of Convolutional Neural Networks

H. Xiong, L. Huang, M. Yu, L. Liu, F. Zhu, L. Shao

Comments International Conference on Machine Learning (ICML) 2020

Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?

Kei Ota, Tomoaki Oiki, Devesh K. Jha, Toshisada Mariyama, Daniel Nikovski

Comments 11 pages, 10 figures. Accepted to ICML 2020

On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings

Mahmoud Assran, Michael Rabbat

Journal ref International Conference on Machine Learning (ICML 2020)

Preference Modeling with Context-Dependent Salient Features

Amanda Bower, Laura Balzano

Comments This is the ICML camera ready version. The main difference is that the statements of the theorems now hold with arbitrary probability δinstead of with probability 1-2/d

Journal ref ICML 2020

Self-Concordant Analysis of Frank-Wolfe Algorithms

Pavel Dvurechensky, Petr Ostroukhov, Kamil Safin, Shimrit Shtern, Mathias Staudigl

Comments Proceedings of the 37th International Conference on Machine Learning (ICML2020)

Recurrent Hierarchical Topic-Guided RNN for Language Generation

Dandan Guo, Bo Chen, Ruiying Lu, Mingyuan Zhou

Comments ICML 2020

Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptation

Amr Alexandari, Anshul Kundaje, Avanti Shrikumar

Comments ICML 2020

What can I do here? A Theory of Affordances in Reinforcement Learning

Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, David Abel, Doina Precup

Comments Thirty-seventh International Conference on Machine Learning (ICML 2020)

On the Generalization Benefit of Noise in Stochastic Gradient Descent

Samuel L. Smith, Erich Elsen, Soham De

Comments Camera-ready version of ICML 2020

Continual Learning from the Perspective of Compression

Xu He, Min Lin

Comments 4th Lifelong Learning Workshop at ICML 2020

Stochastic Differential Equations with Variational Wishart Diffusions

Martin Jørgensen, Marc Peter Deisenroth, Hugh Salimbeni

Comments ICML 2020

Leveraging Frequency Analysis for Deep Fake Image Recognition

Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, Thorsten Holz

Comments Accepted to ICML 2020. New experiments, updated several sections, code: https://github.com/RUB-SysSec/GANDCTAnalysis

Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization

Zhize Li, Dmitry Kovalev, Xun Qian, Peter Richtárik

Comments ICML 2020

Learning Autoencoders with Relational Regularization

Hongteng Xu, Dixin Luo, Ricardo Henao, Svati Shah, Lawrence Carin

Journal ref International conference on machine learning 2020

Differentiable Product Quantization for End-to-End Embedding Compression

Ting Chen, Lala Li, Yizhou Sun

Comments ICML'2020. Code at https://github.com/chentingpc/dpq_embedding_compression

GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

Marc Brockschmidt

Comments As published in ICML 2020 proceedings

Entropy Minimization In Emergent Languages

Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni

Comments Accepted at ICML 2020

Likelihood-free MCMC with Amortized Approximate Ratio Estimators

Joeri Hermans, Volodimir Begy, Gilles Louppe

Comments v5: Camera-ready version presented at ICML 2020