ABSTRACT: The information in the weights of deep networks plays a key role in understanding their behavior. I will describe several results connecting the optimization [...]
ACM's annual elections for its leadership positions. Mong auditorium would allow our 200+ officer core to attend in person to listen to speeches and interact [...]
ABSTRACT: Can we balance efficiency and reliability while designing assistive AI systems? What would such AI systems need to provide? In this talk I will [...]
ABSTRACT: Formal methods is the theory and practice of using mathematically precise specification and proof to demonstrate properties of hardware and software systems. We will [...]
ABSTRACT: Locally Differentially Private (LDP) Reports are commonly used for collection of statistics and machine learning in the federated setting. Yet for both frequency estimation [...]
ABSTRACT: A sparse neural network (NN) has most of its parameters set to zero and is traditionally considered as the product of NN compression (i.e., [...]