PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing
Comments Accepted to ICML 2020 WHI
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks
Comments Presented at the ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning
A Critical Evaluation of Open-World Machine Learning
Comments Presented at the ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning
Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions
Comments 23 pages, 10 tables, 13 figures, to appear in the ICML 2020 Workshop on Graph Representation Learning and Beyond (GRLB)
Attribution Methods Reveal Flaws in Fingerprint-Based Virtual Screening
Comments 4 pages, 5 figures. In proceedings for the 2020 ICML workshop on Machine Learning Interpretability for Scientific Discovery
Emergence of Separable Manifolds in Deep Language Representations
Comments 9 pages. 10 figures. Accepted to ICML 2020. Included supplemental materials
Learning distributed representations of graphs with Geo2DR
Comments 9 Pages, Revised version accepted at ICML 2020 GRL+ Workshop
Implicit Geometric Regularization for Learning Shapes
Comments 37th International Conference on Machine Learning, Vienna, Austria, 2020
Provable Self-Play Algorithms for Competitive Reinforcement Learning
Comments Appearing at ICML 2020. Fixed typos from v1
RicciNets: Curvature-guided Pruning of High-performance Neural Networks Using Ricci Flow
Comments To appear at ICML 2020, AutoML Workshop. Contains 11 pages, 5 figures
Diverse Ensembles Improve Calibration
Comments Presented at the ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning
Analysis of Predictive Coding Models for Phonemic Representation Learning in Small Datasets
Comments 7 pages, 5 figures, 5 tables. Accepted paper at the workshop on Self-supervision in Audio and Speech at ICML 2020
Stochastic Hamiltonian Gradient Methods for Smooth Games
Comments ICML 2020 - Proceedings of the 37th International Conference on Machine Learning
Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Comments ICML 2020
Sharp Analysis of Smoothed Bellman Error Embedding
Comments Accepted at the ICML 2020 Workshop on Theoretical Foundations of Reinforcement Learning
Deep Graph Random Process for Relational-Thinking-Based Speech Recognition
Comments Accepted at ICML 2020
COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations
Comments 8 pages, 1 figure, workshop on Self-supervision in Audio and Speech at the 37th International Conference on Machine Learning (ICML), 2020, Vienna, Austria
Predictive Sampling with Forecasting Autoregressive Models
Comments Accepted at the 37th International Conference on Machine Learning (ICML 2020). 14 pages, 13 figures
Backdoor attacks and defenses in feature-partitioned collaborative learning
Comments to be published in FL-ICML 2020 workshop
Imitation Learning Approach for AI Driving Olympics Trained on Real-world and Simulation Data Simultaneously
Comments Accepted to the Workshop on AI for Autonomous Driving (AIAD), the 37th International Conference on Machine Learning (ICML2020)
Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
Comments arXiv admin note: text overlap with arXiv:1910.05804
Journal ref International Conference on Machine Learning, 2020
Group Equivariant Deep Reinforcement Learning
Comments Presented at the ICML 2020 Workshop on Inductive Biases, Invariances and Generalization in RL
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
Comments Accepted by ICML'2020
Single Shot MC Dropout Approximation
Comments Presented at the ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning
Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks
Comments ICML'20 Workshop on Uncertainty and Robustness in Deep Learning
Interpreting Stellar Spectra with Unsupervised Domain Adaptation
Comments 4 pages, 4 figure, accepted to the ICML 2020 Machine Learning Interpretability for Scientific Discovery workshop. A full 20-page version is submitted to ApJ. The code used in this study is made publicly available on github: https://github.com/teaghan/Cycle_SN
Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models
Comments Accepted to be presented at the ICML Workshop on "Challenges in Deploying and monitoring Machine Learning Systems", 2020. Source code at this link https://github.com/lfwa/carbontracker/
On Class Orderings for Incremental Learning
Comments Accepted at CL-ICML 2020. First two authors contributed equally
Lung Segmentation from Chest X-rays using Variational Data Imputation
Comments Accepted to be presented at the first Workshop on the Art of Learning with Missing Values (Artemiss) hosted by the 37th International Conference on Machine Learning (ICML). Source code, training data and the trained models are available here: https://github.com/raghavian/lungVAE/
FACT: A Diagnostic for Group Fairness Trade-offs
Comments Accepted to International Conference on Machine Learning (ICML 2020)
