We establish new results on the complexity of computing the VC-dimension, including fixed-parameter algorithms and running time lower bounds under the Exponential Time Hypothesis.

Enhancing linear RNNs to multi-dimensional structures, stable and parallelizable.

We develop local algorithms for estimating hitting times and effective resistances.

We develop a policy for adaptive exploration on a graph under frontier constraint that is optimal for trees based on Gittins index, and show how we can apply it to network-based testing in public health settings