9 papers
A fast diagonalization algorithm to enable singular value decomposition of large matrices for efficient template matching
Matthew Giammar, Bronwyn Lucas, Alexander Strang
Many computational problems possess the following three features: (1) the problem could be solved efficiently if a linear operator could be diagonalized, (2) direct diagonalization…
Sample continuation in Bayesian hierarchical model via variational inference
Yucong Liu, Zilai Si, Alexander Strang
Posterior distributions arising in ill-posed Bayesian inverse problems are often both analytically intractable and highly sensitive to parameters of the chosen prior family. We aim…
Do Generalized-Gamma Scale Mixtures of Normals Fit Large Image Datasets?
Brandon Marks, Yash Dave, Zixun Wang +5
A scale mixture of normals is a distribution formed by mixing a collection of normal distributions with fixed mean but different variances. A generalized gamma scale mixture draws…
Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks
Guillaume Corlouer, Avi Semler, Alexander Strang +1
Deep linear networks (DLNs) are used as an analytically tractable model of the training dynamics of deep neural networks. While gradient descent in DLNs is known to exhibit saddle-…
On the Local Structure and Approximation Stability of Block Isotropic Gaussian Fields
Munki Jeong, Alexander Strang
Skew-symmetric functions are a class of functions defined on a product space that are antisymmetric with respect to the order of their inputs. In [13], the authors pro…
Disc Game Dynamics: A Latent Space Perspective on Selection and Learning in Games
Pablo Lechon-Alonso, Andrew Dennehy, Ruizheng Bai +5
Evolutionary game theory studies populations that change in response to an underlying game. Often, the functional form relating outcome to player attributes or strategy is complex,…