226 citations · 1.9k across the 128 of their papers we have counts for
12 papers · 1 filter
Time varying regression with hidden linear dynamics
Ali Jadbabaie, Horia Mania, Devavrat Shah +1
We revisit a model for time-varying linear regression that assumes the unknown parameters evolve according to a linear dynamical system. Counterintuitively, we show that when the u…
Max-Margin Contrastive Learning
Anshul Shah, Suvrit Sra, Rama Chellappa +1
Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence. We suspect this behavio…
Positive definite functions of noncommuting contractions, Hua-Bellman matrices, and a new distance metric
Suvrit Sra
We study positive definiteness of Hua-Bellman matrices (i.e., matrices of the form , where and are strict contractions and $α\in\mathbb{R}…
Introducing Discrepancy Values of Matrices with Application to Bounding Norms of Commutators
Pourya Habib Zadeh, Suvrit Sra
We introduce discrepancy values, quantities inspired by the notion of the spectral spread of Hermitian matrices. We define them as the discrepancy between two consecutive Ky-Fan-li…
Understanding Riemannian Acceleration via a Proximal Extragradient Framework
Jikai Jin, Suvrit Sra
We contribute to advancing the understanding of Riemannian accelerated gradient methods. In particular, we revisit Accelerated Hybrid Proximal Extragradient(A-HPE), a powerful fram…
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond
Chulhee Yun, Shashank Rajput, Suvrit Sra
In distributed learning, local SGD (also known as federated averaging) and its simple baseline minibatch SGD are widely studied optimization methods. Most existing analyses of thes…