304 citations · 1.5k across the 44 of their papers we have counts for
5 papers · 1 filter
An Analytical Characterization of Sloppiness in Neural Networks: Insights from Linear Models
Jialin Mao, Itay Griniasty, Yan Sun +3
Recent experiments have shown that training trajectories of multiple deep neural networks with different architectures, optimization algorithms, hyper-parameter settings, and regul…
Comparing analytic and data-driven approaches to parameter identifiability: A power systems case study
Nikolaos Evangelou, Alexander M. Stankovic, Ioannis G. Kevrekidis +1
Parameter identifiability refers to the capability of accurately inferring the parameter values of a model from its observations (data). Traditional analysis methods exploit analyt…
An information-matching approach to optimal experimental design and active learning
Yonatan Kurniawan, Tracianne B. Neilsen, Benjamin L. Francis +7
The efficacy of mathematical models heavily depends on the quality of the training data, yet collecting sufficient data is often expensive and challenging. Many modeling applicatio…
The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
Jialin Mao, Itay Griniasty, Han Kheng Teoh +5
We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training. By examining the underlying high-dimensional probabilis…
A picture of the space of typical learnable tasks
Rahul Ramesh, Jialin Mao, Itay Griniasty +5
We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-superv…