Thomas Goldstein

Learn More
The alternating direction method of multipliers (ADMM) is a versatile tool for solving a wide range of constrained optimization problems, with differentiable or non-differentiable objective functions. Unfortunately, its performance is highly sensitive to a penalty parameter, which makes ADMM often unreliable and hard to automate for a non-expert user. We(More)
We introduce a new method for location recovery from pair-wise directions that leverages an efficient convex program that comes with exact recovery guarantees, even in the presence of adversarial out-liers. When pairwise directions represent scaled relative positions between pairs of views (estimated for instance with epipolar geometry) our method can be(More)
Stokes and anti-Stokes Raman scattering are performed on atomic layers of hexagonal molybdenum ditelluride (MoTe2), a prototypical transition metal dichalcogenide (TMDC) semiconductor. The data reveal all six types of zone center optical phonons, along with their corresponding Davydov splittings, which have been challenging to see in other TMDCs. We(More)
The increasing complexity of deep learning architectures is resulting in training time requiring weeks or even months. This slow training is due in part to "vanishing gradients," in which the gradients used by back-propagation are extremely large for weights connecting deep layers (layers near the output layer), and extremely small for shallow layers (near(More)
  • 1