Probably Approximately Metric-Fair Learning
Comments Published in International Conference on Machine Learning (ICML) 2018
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
RLlib: Abstractions for Distributed Reinforcement Learning
Comments Published in the International Conference on Machine Learning (ICML 2018), 10 pages
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Comments Accepted to ICML 2018, code opensourced at: https://github.com/rubai5/ESS_Game
Adversarially Regularized Autoencoders
Comments ICML 2018
Learning Implicit Generative Models with the Method of Learned Moments
Comments ICML 2018, 6 figures, 17 pages
Hierarchical Reinforcement Learning with Abductive Planning
Comments 7 pages, 6 figures, ICML/IJCAI/AAMAS 2018 Workshop on Planning and Learning (PAL-18)
Attention-based Deep Multiple Instance Learning
Comments ICML 2018 paper, code source: https://github.com/AMLab-Amsterdam/AttentionDeepMIL
Adversarial Distillation of Bayesian Neural Network Posteriors
Comments accepted at ICML 2018
Generating Counterfactual Explanations with Natural Language
Comments presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
On the Implicit Bias of Dropout
Comments 17 pages, 3 figures, In Proceedings of the Thirty-fifth International Conference on Machine Learning (ICML), 2018
Why Interpretability in Machine Learning? An Answer Using Distributed Detection and Data Fusion Theory
Comments presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
Representation Learning on Graphs with Jumping Knowledge Networks
Comments ICML 2018, accepted as a long oral presentation
Inducing Regular Grammars Using Recurrent Neural Networks
Comments Accepted to L&R 2018 workshop, ICML & IJCAI
Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach
Comments presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations
Comments ICML 2018. arXiv admin note: text overlap with arXiv:1711.03067
Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
Comments Accepted by ICML 2018
Deep SNP: An End-to-end Deep Neural Network with Attention-based Localization for Break-point Detection in SNP Array Genomic data
Comments Accepted at the Joint ICML and IJCAI 2018 Workshop on Computational Biology
Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models
Comments Proceedings of the 30th International Conference on Machine Learning. 2018, to appear. 16 pages, 5 figures
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
Comments ICML 2018
DRACO: Byzantine-resilient Distributed Training via Redundant Gradients
Comments Accepted by ICML 2018
Clipped Action Policy Gradient
Comments Accepted at ICML 2018
Variational Attention for Sequence-to-Sequence Models
Comments In Proceedings of COLING 2018. Also accepted by TADGM Workshop@ICML 2018 for presentation
Interpretable Discovery in Large Image Data Sets
Comments Presented at the 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization
Comments Accepted by ICML 2018
On the Robustness of Interpretability Methods
Comments presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
A Note on the Inception Score
Comments Proc. ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models
A Distributed Second-Order Algorithm You Can Trust
Comments appearing at ICML 2018 - Proceedings of the 35th International Conference on Machine Learning, Stockholm, Schweden, PMLR 80, 2018
Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems
Comments presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
Defining Locality for Surrogates in Post-hoc Interpretablity
Comments presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
Contrastive Explanations with Local Foil Trees
Comments presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
