Tackling covariate shift with node-based Bayesian neural networks
Comments Published at ICML 2022 (long oral presentation). Code is available at https://github.com/AaltoPML/node-BNN-covariate-shift
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
Comments Accepted by ICML 2022
Gradient Descent on Neurons and its Link to Approximate Second-Order Optimization
Comments ICML 2022, camera ready
Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function
Comments Accepted to ICML 2022. 29 pages, 5 figures, 2 tables
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
Comments Accepted to ICML 2022
Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance
Comments 15 pages, 5 figures, ICML'2022
Anarchic Federated Learning
Comments Accepted for Long Presentation in ICML 2022
Linear Bandit Algorithms with Sublinear Time Complexity
Comments Accepted at ICML 2022
Revisiting End-to-End Speech-to-Text Translation From Scratch
Comments ICML
Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization
Comments Accepted as a Spotlight paper at ICML 2022. 27 pages, 10 figures
Choosing Answers in $\varepsilon$-Best-Answer Identification for Linear Bandits
Comments 47 pages, 10 figures, 8 tables. To be published in the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022
Contextual Information-Directed Sampling
Comments Accepted at ICML 2022
A Psychological Theory of Explainability
Comments 15 pages, 3 figures, ICML 2022
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization
Comments 25 pages with 10 figures, accepted for publication in ICML 2022 (Our code is available at https://github.com/sony/sqvae)
Understanding the unstable convergence of gradient descent
Comments Accepted to the 39th International Conference on Machine Learning (ICML 2022), Baltimore, Maryland, USA. Version 2 improves writing and presentation, adds discussion regarding concurrent works
Label-Free Explainability for Unsupervised Models
Comments Presented at ICML 2022
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
Comments Accepted to ICML'2022. Code and models are available at https://github.com/neulab/retomaton
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Comments Accepted by ICML 2022
Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing
Comments 35 pages, 8 figures, to appear in International Conference on Machine Learning (ICML), 2022
Generalization and Robustness Implications in Object-Centric Learning
Comments Published at ICML 2022
A Study of Face Obfuscation in ImageNet
Comments Accepted to ICML 2022
Generative Flow Networks for Discrete Probabilistic Modeling
Comments Accepted by ICML 2022
A Self-Supervised Automatic Post-Editing Data Generation Tool
Comments Accepted for DataPerf workshop at ICML 2022
Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
Comments In the 39th International Conference on Machine Learning (ICML 2022)
Selective Network Linearization for Efficient Private Inference
Comments Published in ICML 2022
Inverse Contextual Bandits: Learning How Behavior Evolves over Time
Comments In Proceedings of the 39th International Conference on Machine Learning
Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations
Comments 14 pages, 5 figures, Accepted by ICML 2021 Workshop on Adversarial Machine Learning
Building Robust Ensembles via Margin Boosting
Comments Accepted by ICML 2022
Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images
Comments 12 pages, 5 figures. In proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022. Copyright 2022 by the author(s)
Reachability Constrained Reinforcement Learning
Comments Accepted by ICML 2022
