On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning
Comments Accepted to ICML 2023
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Multi-Modal Classifiers for Open-Vocabulary Object Detection
Comments ICML 2023, project page: https://www.robots.ox.ac.uk/vgg/research/mm-ovod/
Task-specific experimental design for treatment effect estimation
Comments To appear in ICML 2023; 8 pages, 7 figures, 4 appendices
Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum
Comments ICML 2023, first two authors contributed equally
SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
Comments ICML'23
Efficient Personalized Federated Learning via Sparse Model-Adaptation
Comments Accepted to ICML 2023
Reflected Diffusion Models
Comments ICML 2023 Camera Ready. Code available at https://github.com/louaaron/Reflected-Diffusion
Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games
Comments Accepted for publication at ICML 2023
Action Matching: Learning Stochastic Dynamics from Samples
Comments Published in ICML 2023
OCD: Learning to Overfit with Conditional Diffusion Models
Comments Accepted to ICML 2023 (Oral & Poster)
Scaling Spherical CNNs
Comments Accepted to ICML'23
Improving Visual Prompt Tuning for Self-supervised Vision Transformers
Comments International Conference on Machine Learning (ICML) 2023
Robust Subtask Learning for Compositional Generalization
Journal ref Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023
FARE: Provably Fair Representation Learning with Practical Certificates
Comments ICML 2023
Non-autoregressive Conditional Diffusion Models for Time Series Prediction
Comments Accepted by ICML 2023 (Poster)
Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning
Comments 22 pages, accepted at ICML 2023
The Ideal Continual Learner: An Agent That Never Forgets
Comments Accepted to ICML 2023
Controlled Text Generation with Natural Language Instructions
Comments ICML 2023
Robust Non-Linear Feedback Coding via Power-Constrained Deep Learning
Comments To appear in International Conference on Machine Learning (ICML) 2023
Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models
Comments Accepted in ICML 2023
Learning to Maximize Mutual Information for Dynamic Feature Selection
Comments ICML 2023 camera-ready
Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation
Comments ICML 2023
Open-Vocabulary Universal Image Segmentation with MaskCLIP
Comments ICML 2023 Camera Ready
Training-Free Neural Active Learning with Initialization-Robustness Guarantees
Comments Accepted to 40th International Conference on Machine Learning (ICML 2023), 41 pages
Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time
Comments To appear in the Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023
Effective Neural Topic Modeling with Embedding Clustering Regularization
Comments Accepted to ICML 2023 conference
Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models
Comments International Conference on Machine Learning (ICML) 2023
One-sided Matrix Completion from Two Observations Per Row
Comments ICML 2023
Randomized Schur Complement Views for Graph Contrastive Learning
Comments ICML 2023
Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels
Comments ICML 2023
