fisher information

On the Convergence of the Shapley Value in Parametric Bayesian Learning Games ICML 2022 Task Affinity with Maximum Bipartite Matching in Few-Shot Learning ICLR 2022 Towards a Theory of Non-Log-Concave Sampling:First-Order Stationarity Guarantees for Langevin Monte Carlo COLT 2022 Unifying Importance Based Regularisation Methods for Continual Learning AISTATS 2022 Adversarial Training Reduces Information and Improves Transferability AAAI 2021 An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers NeurIPS 2021 Gone Fishing: Neural Active Learning with Fisher Embeddings NeurIPS 2021 Group Fisher Pruning for Practical Network Compression ICML 2021 Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding NAACL 2021 Interactive Label Cleaning with Example-based Explanations NeurIPS 2021 Learning to live with Dale's principle: ANNs with separate excitatory and inhibitory units ICLR 2021 Measuring data leakage in machine-learning models with Fisher information UAI 2021 On Uninformative Optimal Policies in Adaptive LQR with Unknown B-Matrix L4DC 2021 Pointwise Bounds for Distribution Estimation under Communication Constraints NeurIPS 2021 Regularising Fisher Information Improves Cross-lingual Generalisation EMNLP 2021 Training Neural Networks with Fixed Sparse Masks NeurIPS 2021 Adaptation Properties Allow Identification of Optimized Neural Codes NeurIPS 2020 BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget ICLR 2020 Information-Theoretic Local Minima Characterization and Regularization ICML 2020 Lower Bounds for Learning Distributions under Communication Constraints via Fisher Information JMLR 2020 Minimax Bounds for Generalized Linear Models NeurIPS 2020 On the interplay between noise and curvature and its effect on optimization and generalization AISTATS 2020 PEP: Parameter Ensembling by Perturbation NeurIPS 2020 Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies NeurIPS 2020 Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks NeurIPS 2020