Statistical Learning
FedPop: A Bayesian Approach for Personalised Federated Learning
Personalised federated learning (FL) aims at collaboratively learning a machine learning model tailored for each client.
Single Model Uncertainty Estimation via Stochastic Data Centering
UQ's uncertainty estimates are superior to many of the current methods
Generalization Bounds for Estimating Causal Effects of Continuous Treatments
We focus on estimating causal effects of continuous treatments (e.g., dosage in medicine), also known as dose-response function.
Empirical Gateaux Derivatives for Causal Inference Michael I. Jordan
We study a constructive algorithm that approximates Gateaux derivatives for statistical functionals by finite differencing, with a focus on functionals that arise in causal inference. We study the setting where probability distributions are not known a priori but need to be estimated from data. These estimated distributions lead to empirical Gateaux derivatives, and we study the relationships between empirical, numerical, and analytical Gateaux derivatives.
RecursiveMix: Mixed Learning with History Lingfeng Y ang
Mix-based augmentation has been proven fundamental to the generalization of deep vision models.
Neural Basis Models for Interpretability
However, these models are typically difficult to train, require numerous parameters, and are difficult to scale.
Factored DRO: Factored Distributionally Robust Policies for Contextual Bandits
Prior work that either ignores potential shifts in the context, or considers them jointly, can lead to performance that is too conservative, especially under certain forms of reward feedback.
Attention-based Neural Cellular Automata
Recent extensions of Cellular Automata (CA) have incorporated key ideas from modern deep learning, dramatically extending their capabilities and catalyzing a new family of Neural Cellular Automata (NCA) techniques.