6 papers
BLISS: Global Blind Identification of Linear Systems with Sparse Inputs
Kyle Poe, Uday Kiran Reddy Tadipatri, Benjamin D. Haeffele +1
Linear system identification and sparse dictionary learning can both be seen as structured matrix factorization problems. However, these two problems have historically been studied…
An Overview of Low-Rank Structures in the Training and Adaptation of Large Models
Laura Balzano, Tianjiao Ding, Benjamin D. Haeffele +5
The substantial computational demands of modern large-scale deep learning present significant challenges for efficient training and deployment. Recent research has revealed a wides…
Adaptive Stain Normalization for Cross-Domain Medical Histology
Tianyue Xu, Yanlin Wu, Abhai K. Tripathi +2
Deep learning advances have revolutionized automated digital pathology analysis. However, differences in staining protocols and imaging conditions can introduce significant color v…
Nonconvex Linear System Identification with Minimal State Representation
Uday Kiran Reddy Tadipatri, Benjamin D. Haeffele, Joshua Agterberg +2
Low-order linear System IDentification (SysID) addresses the challenge of estimating the parameters of a linear dynamical system from finite samples of observations and control inp…
A Convex Relaxation Approach to Generalization Analysis for Parallel Positively Homogeneous Networks
Uday Kiran Reddy Tadipatri, Benjamin D. Haeffele, Joshua Agterberg +1
We propose a general framework for deriving generalization bounds for parallel positively homogeneous neural networks--a class of neural networks whose input-output map decomposes…
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
Ziyang Wu, Tianjiao Ding, Yifu Lu +6
The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However,…