-
healthcare application needs to analyze sensitive patient data across distributed nodes. Researchers and students can explore privacy-preserving algorithms and technologies like federated learning and zero
-
at one time. In non-stationary environments on the other hand, the same algorithms cannot be applied as the underlying data distributions change constantly and the same models are not valid. Hence, we need
-
. The project will focus on automated distributional shift detection and monitoring, invariant and distributionally robust representation learning algorithms, and deployment-time calibration with uncertainty
-
Federated learning (FL) is an emerging machine learning paradium to enable distributed clients (e.g., mobile devices) to jointly train a machine learning model without pooling their raw data into a
-
estimation methods for deep neural networks. A principled Bayesian framework for multimodal uncertainty modeling. Robust learning algorithms under missing modalities and distribution shifts. New uncertainty
-
Education Bayesian Uncertainty Estimation for Robust Single- and Multi-View Learning in CV and NLP Robust Active Learning Under Distribution Drift Data-Efficient Deep Learning for De Novo Molecular Design
-
comparing models with entirely different structures and parameter counts, whether comparing linear regression against mixture models or decision trees. MML is strictly Bayesian, requiring prior distributions
-
. Wallace (1996). MML estimation of the parameters of the spherical Fisher Distribution. In S. Arikawa and A. K. Sharma (eds.), Proc. 7th International Workshop on Algorithmic Learning Theory (ALT'96
-
-readable representations, such as distributed representations of text augmented with random noises [1] or unnatural text curated by replacing sensitive tokens with random non-sensitive ones [2]. First, such
-
The relationship between the information-theoretic Bayesian minimum message length (MML) principle and the notion of Solomonoff-Kolmogorov complexity from algorithmic information theory (Wallace and