3 papers
cs.LG2019
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
Rohith Kuditipudi, Xiang Wang, Holden Lee +5
Mode connectivity is a surprising phenomenon in the loss landscape of deep nets. Optima -- at least those discovered by gradient-based optimization -- turn out to be connected by s…
cs.IT2019
Minimizing the Number of Detrimental Objects in Multi-Dimensional Graph-Based Codes
Ahmed Hareedy, Rohith Kuditipudi, Robert Calderbank
In order to meet the demands of data-hungry applications, data storage devices are required to be increasingly denser. Various sources of error appear with this increase in density…
cs.LG2018
Learning Two-layer Neural Networks with Symmetric Inputs
Rong Ge, Rohith Kuditipudi, Zhize Li +1
We give a new algorithm for learning a two-layer neural network under a general class of input distributions. Assuming there is a ground-truth two-layer network $$ y = A σ(Wx) + ξ,…