We present a viable algorithm for the problem of optimally covering a compact set with a fixed number of balls using results from sensitivity analysis and nonsmooth and nonconvex optimization.

We propose an adaptive subset selection framework for supervised learning, where submodular functions quantify sample difficulty to guide curriculum learning.

Risk awareness in Early Exit DNNs

We solve an under explored setting of domain generalization in generalized category discovery, where the unlabeled target domain is unknown till inference.

A first lower bounds for regret of decentralized multi-agent-SSP.