Adversarial representation learning for private speech generation
Comments Submitted to ICML 2020 Workshop on Self-supervision in Audio and Speech (SAS)
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Multi-Precision Policy Enforced Training (MuPPET): A precision-switching strategy for quantised fixed-point training of CNNs
Comments Accepted at the 37th International Conference on Machine Learning (ICML), 2020
DeepCoDA: personalized interpretability for compositional health data
Comments To appear at ICML 2020
Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML
Comments ICML 2020
Probabilistic Decoupling of Labels in Classification
Comments Submitted to ICML 2020 (not accepted)
From Local SGD to Local Fixed-Point Methods for Federated Learning
Comments Accepted to ICML 2020
Nearly Linear Row Sampling Algorithm for Quantile Regression
Comments Accepted to ICML 2020
Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent
Comments to appear in ICML 2020
Learning for Dose Allocation in Adaptive Clinical Trials with Safety Constraints
Comments Accepted to the 37th International Conference on Machine Learning (ICML 2020)
Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting
Comments 39 pages, 25 figures. Proceedings of the 37th International Conference on Machine Learning (ICML), Vienna, Austria, PMLR 108, 2020
Optimization Theory for ReLU Neural Networks Trained with Normalization Layers
Comments To be presented at ICML 2020
Invariant Causal Prediction for Block MDPs
Comments Accepted to ICML 2020. 16 pages, 8 figures
NADS: Neural Architecture Distribution Search for Uncertainty Awareness
Comments ICML 2020
Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction
Comments Submitted to the ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, Vienna, Austria, 2020
Interferometric Graph Transform: a Deep Unsupervised Graph Representation
Journal ref International Conference on Machine Learning (ICML), 2020, Online, Austria
Contrastive Multi-View Representation Learning on Graphs
Comments ICML 2020
Do RNN and LSTM have Long Memory?
Comments Accepted by ICML 2020. Added references, experiments and acknowledgements
Almost Tune-Free Variance Reduction
Journal ref ICML 2020
Optimal Continual Learning has Perfect Memory and is NP-hard
Comments Accepted for publication at ICML (International Conference on Machine Learning) 2020; 13 pages, 8 Figures
AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation
Comments accepted in ICML 2020
Learning to Stop While Learning to Predict
Comments Proceedings of the 37th International Conference on Machine Learning
Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization
Comments ICML 2020
Learning to Branch for Multi-Task Learning
Comments Accepted at ICML 2020
Multi-Agent Determinantal Q-Learning
Comments ICML 2020
NGBoost: Natural Gradient Boosting for Probabilistic Prediction
Comments Accepted for ICML 2020
On Universalized Adversarial and Invariant Perturbations
Comments Some part of this work was presented in ICML 2018 Workshop on "Towards learning with limited labels: Equivariance, Invariance,and Beyond" as "Understanding Adversarial Robustness of Symmetric Networks"
Undirected Graphical Models as Approximate Posteriors
Comments Accepted to ICML 2020
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
Comments Accepted by ICML 2020, 21 pages, 1 figure
Learning to Rank Learning Curves
Comments Accepted at the International Conference on Machine Learning (ICML) 2020
Debiased Sinkhorn barycenters
Comments ICML 2020
