57 citations · 143 across the 11 of their papers we have counts for
5 papers · 1 filter
Optimization Can Learn Johnson Lindenstrauss Embeddings
Nikos Tsikouras, Constantine Caramanis, Christos Tzamos
Embeddings play a pivotal role across various disciplines, offering compact representations of complex data structures. Randomized methods like Johnson-Lindenstrauss (JL) provide s…
Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD
Matthew Faw, Litu Rout, Constantine Caramanis +1
This work considers the problem of finding a first-order stationary point of a non-convex function with potentially unbounded smoothness constant using a stochastic gradient oracle…
A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models
Litu Rout, Advait Parulekar, Constantine Caramanis +1
We provide a theoretical justification for sample recovery using diffusion based image inpainting in a linear model setting. While most inpainting algorithms require retraining wit…
Greedy Subspace Clustering
Dohyung Park, Constantine Caramanis, Sujay Sanghavi
We consider the problem of subspace clustering: given points that lie on or near the union of many low-dimensional linear subspaces, recover the subspaces. To this end, one first i…
Principal Component Analysis with Contaminated Data: The High Dimensional Case
Huan Xu, Constantine Caramanis, Shie Mannor
We consider the dimensionality-reduction problem (finding a subspace approximation of observed data) for contaminated data in the high dimensional regime, where the number of obser…