Routing Networks with Co-training for Continual Learning
Comments Presented at ICML Workshop on Continual Learning 2020
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Multilinear Latent Conditioning for Generating Unseen Attribute Combinations
Comments published at International Conference on Machine Learning 2020
Hierarchical Expert Networks for Meta-Learning
Comments Presented at the 4th ICML Workshop on Life Long Machine Learning, 2020
Modulating Surrogates for Bayesian Optimization
Journal ref 37th International Conference On Machine Learning (ICML 2020)
Estimating Risk and Uncertainty in Deep Reinforcement Learning
Comments Work presented at the ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning
Variational Bayesian Quantization
Comments 9 pages + detailed supplement with additional full resolution reconstructed images; ICML 2020 final camera-ready version, title changed to "Variational Bayesian Quantization" following reviewer feedback
PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination
Comments Accepted at ICML 2020
How does Early Stopping Help Generalization against Label Noise?
Comments International Conference on Machine Learning, Workshop on Uncertainty and Robustness in Deep Learning. See: https://sites.google.com/view/udlworkshop2020/home
An industry case of large-scale demand forecasting of hierarchical components
Journal ref 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)
Escaping Saddle Points in Ill-Conditioned Matrix Completion with a Scalable Second Order Method
Comments 15 pages, presented at the Workshop on "Beyond first-order methods in ML systems" at the $37^th$ International Conference on Machine Learning (ICML), Vienna, Austria, 2020
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
Comments Thirty-seventh International Conference on Machine Learning (ICML 2020)
Progressive Identification of True Labels for Partial-Label Learning
Comments In Proceedings of the 37th International Conference on Machine Learning (ICML 2020)
On the Expressivity of Neural Networks for Deep Reinforcement Learning
Comments Accepted in ICML 2020. Title of previous version was "Bootstrapping the Expressivity with Model-based Planning". Code is available at https://github.com/roosephu/boots
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
Comments In Proceedings of the 37th International Conference on Machine Learning (ICML). July 2020
Which Tasks Should Be Learned Together in Multi-task Learning?
Comments Presented to ICML 2020 See project website at http://taskgrouping.stanford.edu/
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Comments The first two authors contributed equally. Accepted at ICML 2020. Supplementary videos and code available at: https://sites.google.com/view/av-detect-recover-adapt
Ordinal Non-negative Matrix Factorization for Recommendation
Comments Accepted for publication at ICML 2020
Robustness to Programmable String Transformations via Augmented Abstract Training
Comments 12 pages, ICML 2020
Uncertainty aware Search Framework for Multi-Objective Bayesian Optimization with Constraints
Comments 9 pages, 2 figures, 1 table
Journal ref 7th ICML Workshop on Automated Machine Learning (2020)
Pattern-Guided Integrated Gradients
Comments Presented at the ICML 2020 Workshop on Human Interpretability in Machine Learning (WHI)
Voice Separation with an Unknown Number of Multiple Speakers
Comments Accepted to ICML 2020. For associated audio samples, see http://enk100.github.io/speaker_separation
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
Comments ICML 2020, project at https://linear-transformers.com/
Full Law Identification In Graphical Models Of Missing Data: Completeness Results
Comments Camera ready version published at ICML 2020
Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119, 2020
Hierarchically Decoupled Imitation for Morphological Transfer
Comments International Conference on Machine Learning (ICML) 2020 camera ready submission
Discriminative Adversarial Search for Abstractive Summarization
Comments ICML 2020
Rate-Distortion Optimization Guided Autoencoder for Isometric Embedding in Euclidean Latent Space
Comments Accepted to the International Conference on Machine Learning (ICML) 2020
Real-world Video Adaptation with Reinforcement Learning
Comments Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 36th International Conference on Machine Learning, Long Beach, California, USA, 2019
Fast Real-time Counterfactual Explanations
Comments This paper has been accepted by ICML workshop 2020
Continuously Indexed Domain Adaptation
Comments Accepted at ICML 2020. Talk: https://www.youtube.com/watch?v=KtZPSCD-WhQ Code and Project Page: https://github.com/hehaodele/CIDA
Bandits with adversarial scaling
Comments Appeared in ICML 2020
