Rohith Kuditipudi

TL;DR: The authors provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e. g.g. model architectures, training procedures, data, systems, security, evaluation, theory) to their applications.

TL;DR: This work gives mathematical explanations for mode connectivity of deep nets, assuming generic properties of well-trained deep nets (such as dropout stability and noise stability) and experiments are presented to verify the theory.

TL;DR: A new algorithm for learning a two-layer neural network under a general class of input distributions based on the method-of-moments framework and extends several results in tensor decompositions to avoid the complicated non-convex optimization in learning neural networks.

TL;DR: In this article, the authors give mathematical explanations for mode connectivity in deep networks, assuming generic properties (such as dropout stability and noise stability) of well-trained deep nets, which have previously been identified as part of understanding the generalization properties of deep nets.

TL;DR: In this article, the authors proposed a method for learning a two-layer neural network under a general class of input distributions, which is based on the method-of-moments framework and extends several tensor decompositions.