Bracha Laufer-Goldshtein

⇒  Select model configurations that control multiple risks while minimizing additional free objectives.

⇒ Combine Multi-Objective Optimization with Multiple Hypothesis Testing. 

⇒ Focus testing on the Pareto Frontier for improved computational and statistical efficiency.

⇒ Application for reliable adaptive computation in large transformer models. 

⇒  Semi-supervised, utilizes a small number of labelled data and a large number of unlabelled data

⇒ Manifold-regularized optimization, impose a smoothness constraint on possible solutions with respect to a manifold learned in a data-driven manner.

⇒ Localization based on ad-hoc networks with several nodes, where each node consists of a compact microphone array​.

⇒  Each node represents a different viewpoint that can be associated with a specific manifold.

⇒  Present a Bayesian paradigm for merging the information of the co-related manifolds.

 

⇒ A data-driven propagation model relating movements on the abstract manifold to the actual source displacements.

⇒  Present a hybrid approach to connect the two different worlds of classical and data-driven localization.

⇒ A novel data-driven geometric approach for source separation, based on a well-established probabilistic model.

⇒  A new representation of the data in a shape of a simplex.

⇒  The simplex dimension corresponds to the number of speakers, and its vertices represent time-intervals with a single dominating speaker.​​

 

⇒ Combine two simplex representations - global and local.

⇒ Global representation provides probability of activity in each frame.

⇒ Local representation provides dominance of speakers in each frequency.

⇒ Obtain the full spectral mask by aligning each of the local representations using the global probabilities.​​