QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
Comments 18 pages; Accepted to ICML 2019
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
Comments Published in the International Conference on Machine Learning, 2019
Convolutional Poisson Gamma Belief Network
Comments ICML 2019
Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
Comments ICML 2019
Dimensionality Reduction for Tukey Regression
Comments To appear in ICML 2019
Replica Conditional Sequential Monte Carlo
Comments To appear in Proceedings of ICML '19
High-Fidelity Image Generation With Fewer Labels
Comments Mario Lucic, Michael Tschannen, and Marvin Ritter contributed equally to this work. ICML 2019 camera-ready version. Code available at https://github.com/google/compare_gan
NAS-Bench-101: Towards Reproducible Neural Architecture Search
Comments Published in the Proceedings of the 36th International Conference on Machine Learning
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities
Journal ref ICML 2019
Gauge Equivariant Convolutional Networks and the Icosahedral CNN
Comments Proceedings of the International Conference on Machine Learning (ICML), 2019
Robust Inference via Generative Classifiers for Handling Noisy Labels
Comments Accepted in ICML 2019
Multi-Frequency Phase Synchronization
Comments 12 pages, 9 figures. ICML 2019
Loss Landscapes of Regularized Linear Autoencoders
Comments 12 pages, 8 figures. ICML 2019
On Connected Sublevel Sets in Deep Learning
Comments Accepted at ICML 2019. More discussions and visualizations are added
First-order algorithms converge faster than $O(1/k)$ on convex problems
Comments In the proceedings of the 36th International Conference on Machine Learning
CompILE: Compositional Imitation Learning and Execution
Comments ICML (2019)
Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD
Journal ref Proceedings of the 36th International Conference on Machine Learning, PMLR 97, 2019
A Kernel Perspective for Regularizing Deep Neural Networks
Comments ICML
A Large-Scale Study on Regularization and Normalization in GANs
Comments Revision accepted to ICML'19: More focus on regularization and normalization aspects. Added recent references and promising future directions
Guarantees for Greedy Maximization of Non-submodular Functions with Applications
Comments published at ICML 2017. First author is now known as Yatao Bian <ybian@inf.ethz.ch>. ORCID: https://orcid.org/0000-0002-2368-4084
Implicit Filter Sparsification In Convolutional Neural Networks
Comments ODML-CDNNR 2019 (ICML'19 workshop) extended abstract of the CVPR 2019 paper "On Implicit Filter Level Sparsity in Convolutional Neural Networks, Mehta et al." (arXiv:1811.12495)
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
Comments Accepted by the 36th International Conference on Machine Learning (ICML 2019)
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement
Comments Accepted by Thirty-sixth International Conference on Machine Learning (ICML) 2019
Hierarchical Importance Weighted Autoencoders
Comments Accepted by ICML 2019. 17 pages
Approximated Oracle Filter Pruning for Destructive CNN Width Optimization
Comments ICML 2019
Rotation Invariant Householder Parameterization for Bayesian PCA
Comments Accepted to ICML 2019
On Graph Classification Networks, Datasets and Baselines
Comments Submitted to the ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data
Learning to Convolve: A Generalized Weight-Tying Approach
Comments Accepted to ICML 2019
Training CNNs with Selective Allocation of Channels
Comments 15 pages; Accepted to ICML 2019
On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization
Comments A short version is accepted to ICML 2019
