Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
Comments ICML 2021
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations
Comments Published in ICML'21. Code and data: https://github.com/pemami4911/EfficientMORL
Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model
Comments Accepted to ICML 2021
Signatured Deep Fictitious Play for Mean Field Games with Common Noise
Comments Published at ICML 2021
Asymmetric Loss Functions for Learning with Noisy Labels
Comments ICML 2021
Self-Damaging Contrastive Learning
Comments ICML 2021
Learning Routines for Effective Off-Policy Reinforcement Learning
Comments ICML 2021
Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
Comments 16 pages, 12 figures; Accepted to ICML 2021
Generative Causal Explanations for Graph Neural Networks
Comments To appear in the Thirty-eighth International Conference on Machine Learning (ICML2021). Source code: https://github.com/wanyu-lin/ICML2021-Gem
Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data
Comments Accepted to ICML 2021; 31 pages,9 figures
Principled Simplicial Neural Networks for Trajectory Prediction
Comments To appear in ICML 2021
An Exact Solver for the Weston-Watkins SVM Subproblem
Comments ICML 2021
Equivariant message passing for the prediction of tensorial properties and molecular spectra
Comments Accepted at ICML 2021
Federated Composite Optimization
Comments Accepted to ICML 2021. Code repository see https://github.com/hongliny/FCO-ICML21
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Comments Accepted to ICML 2021
Federated Accelerated Stochastic Gradient Descent
Comments Accepted to NeurIPS 2020. Best paper in International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2020 (FL-ICML'20). Code repository see https://github.com/hongliny/FedAc-NeurIPS20
Active Covering
Comments ICML 2021
Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
Comments 33 pages, 5 figures, ICML 2021
One-sided Frank-Wolfe algorithms for saddle problems
Comments to appear at ICML 2021
Communication-Efficient Distributed SVD via Local Power Iterations
Comments 9 pages, 7 figures, accepted by 2021 ICML
A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples
Comments 45 pages, 8 figures, to be published in ICML 2021. arXiv admin note: text overlap with arXiv:2009.02905
The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
Comments ICML 2021. The code is available at https://github.com/FloList/EMPL
Near-Optimal Confidence Sequences for Bounded Random Variables
Comments Accepted to ICML 2021
Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning
Comments Accepted at International Conference on Machine Learning (ICML) 2021
A Differentiable Point Process with Its Application to Spiking Neural Networks
Comments Accepted to ICML 2021
Conformal Anomaly Detection on Spatio-Temporal Observations with Missing Data
Comments Submitted to ICML 2021 Workshop--Distribution-free Uncertainty Quantification
Learning to Rehearse in Long Sequence Memorization
Comments Accepted by ICML 2021
Testing Group Fairness via Optimal Transport Projections
Journal ref International Conference on Machine Learning 2021
Offline Reinforcement Learning with Pseudometric Learning
Comments ICML 2021
GraphDF: A Discrete Flow Model for Molecular Graph Generation
Comments Accepted by ICML 2021
