IowaRain: A Statewide Rain Event Dataset Based on Weather Radars and Quantitative Precipitation Estimation
Comments 4 pages, Accepted to Tackling Climate Change with Machine Learning workshop at ICML 2021
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8857-8868, 2021
Differentiable Architecture Pruning for Transfer Learning
Comments 19 pages (main + appendix), 7 figures and 1 table, Workshop @ ICML 2021, 24th July 2021
MD-split+: Practical Local Conformal Inference in High Dimensions
Comments Appearing in ICML 2021 workshop on distribution-free uncertainty quantification
Urban Tree Species Classification Using Aerial Imagery
Comments International Conference on Machine Learning (ICML 2021), Workshop on Tackling Climate Change with Machine Learning
Nonmyopic Multifidelity Active Search
Comments To appear in ICML 2021
Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution
Comments Accepted by ICML 2021
How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference
Journal ref In Proceedings of the International Conference on Machine Learning (ICML) 2021
Path Planning using Neural A* Search
Comments To appear in the International Conference on Machine Learning (ICML 2021)
Finite mixture models do not reliably learn the number of components
Comments Proceedings of the 38th International Conference on Machine Learning (ICML), to appear. 25 pages, 4 figures
Provable Lipschitz Certification for Generative Models
Comments Accepted into ICML 2021
Intrinsic uncertainties and where to find them
Comments Presented at the ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning
Order in the Court: Explainable AI Methods Prone to Disagreement
Comments Accepted for presentation at the ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Comments to be published in ICML 2021
Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
Comments Appears in Proceedings of the 38th International Conference on Machine Learning (ICML), 2021
A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning
Journal ref International Conference on Machine Learning (ICML), 2021
Provably Strict Generalisation Benefit for Equivariant Models
Comments A shortened version appears in ICML 2021
LTL2Action: Generalizing LTL Instructions for Multi-Task RL
Comments International Conference on Machine Learning (ICML) 2021
Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
Journal ref International Conference on Machine Learning (ICML), 2021
Differentiating through the Fréchet Mean
Comments ICML 2020 camera-ready; updated Algorithm 1 typo
Quality Metrics for Transparent Machine Learning With and Without Humans In the Loop Are Not Correlated
Comments Proceedings of the ICML Workshop on Theoretical Foundations, Criticism, and Application Trends of Explainable AI held in conjunction with the 38th International Conference on Machine Learning (ICML), a non-peer-reviewed longer version was previously published as preprint here arXiv:1912.05011
Randomized Dimensionality Reduction for Facility Location and Single-Linkage Clustering
Comments 25 pages. Published as a conference paper in ICML 2021
Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers
Comments Under review at the Uncertainty and Robustness in Deep Learning workshop at ICML 2021. Our appendix is attached to the last page of the paper
Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability
Comments to appear ICML 2021
Temporally Correlated Task Scheduling for Sequence Learning
Comments Accepted to ICML 2021
Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples
Comments ICML 2021 workshop on A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning
Goal-Conditioned Reinforcement Learning with Imagined Subgoals
Comments ICML 2021. See the project webpage at https://www.di.ens.fr/willow/research/ris/
AdaXpert: Adapting Neural Architecture for Growing Data
Comments accepted by ICML 2021
The Interplay between Distribution Parameters and the Accuracy-Robustness Tradeoff in Classification
Comments Accepted for presentation in AML ICML workshop 2021
Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks
Comments Accepted by the ICML 2021 Workshop on A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning(https://openreview.net/group?id=ICML.cc/2021/Workshop/AML)
