Scholarship list
Preprint
A Smoothing Newton Method for Rank-one Matrix Recovery
Published 07/30/2025
arXiv (Cornell University)
We consider the phase retrieval problem, which involves recovering a rank-one positive semidefinite matrix from rank-one measurements. A recently proposed algorithm based on Bures-Wasserstein gradient descent (BWGD) exhibits superlinear convergence, but it is unstable, and existing theory can only prove local linear convergence for higher rank matrix recovery. We resolve this gap by revealing that BWGD implements Newton's method with a nonsmooth and nonconvex objective. We develop a smoothing framework that regularizes the objective, enabling a stable method with rigorous superlinear convergence guarantees. Experiments on synthetic data demonstrate this superior stability while maintaining fast convergence.
Preprint
Global Convergence of Iteratively Reweighted Least Squares for Robust Subspace Recovery
Published 06/29/2025
arXiv (Cornell University)
Robust subspace estimation is fundamental to many machine learning and data analysis tasks. Iteratively Reweighted Least Squares (IRLS) is an elegant and empirically effective approach to this problem, yet its theoretical properties remain poorly understood. This paper establishes that, under deterministic conditions, a variant of IRLS with dynamic smoothing regularization converges linearly to the underlying subspace from any initialization. We extend these guarantees to affine subspace estimation, a setting that lacks prior recovery theory. Additionally, we illustrate the practical benefits of IRLS through an application to low-dimensional neural network training. Our results provide the first global convergence guarantees for IRLS in robust subspace recovery and, more broadly, for nonconvex IRLS on a Riemannian manifold.
Preprint
Preconditioned Subspace Langevin Monte Carlo
Published 12/18/2024
We develop a new efficient method for high-dimensional sampling called Subspace Langevin Monte Carlo. The primary application of these methods is to efficiently implement Preconditioned Langevin Monte Carlo. To demonstrate the usefulness of this new method, we extend ideas from subspace descent methods in Euclidean space to solving a specific optimization problem over Wasserstein space. Our theoretical analysis demonstrates the advantageous convergence regimes of the proposed method, which depend on relative conditioning assumptions common to mirror descent methods. We back up our theory with experimental evidence on sampling from an ill-conditioned Gaussian distribution.
Preprint
Acceleration and Implicit Regularization in Gaussian Phase Retrieval
Published 11/20/2023
We study accelerated optimization methods in the Gaussian phase retrieval problem. In this setting, we prove that gradient methods with Polyak or Nesterov momentum have similar implicit regularization to gradient descent. This implicit regularization ensures that the algorithms remain in a nice region, where the cost function is strongly convex and smooth despite being nonconvex in general. This ensures that these accelerated methods achieve faster rates of convergence than gradient descent. Experimental evidence demonstrates that the accelerated methods converge faster than gradient descent in practice.
Preprint
Bures-Wasserstein Barycenters and Low-Rank Matrix Recovery
Published 10/26/2022
We revisit the problem of recovering a low-rank positive semidefinite matrix
from rank-one projections using tools from optimal transport. More
specifically, we show that a variational formulation of this problem is
equivalent to computing a Wasserstein barycenter. In turn, this new perspective
enables the development of new geometric first-order methods with strong
convergence guarantees in Bures-Wasserstein distance. Experiments on simulated
data demonstrate the advantages of our new methodology over existing methods.
Preprint
Stochastic and Private Nonconvex Outlier-Robust PCA
Published 03/17/2022
ArXiv.org
We develop theoretically guaranteed stochastic methods for outlier-robust PCA. Outlier-robust PCA seeks an underlying low-dimensional linear subspace from a dataset that is corrupted with outliers. We are able to show that our methods, which involve stochastic geodesic gradient descent over the Grassmannian manifold, converge and recover an underlying subspace in various regimes through the development of a novel convergence analysis. The main application of this method is an effective differentially private algorithm for outlier-robust PCA that uses a Gaussian noise mechanism within the stochastic gradient method. Our results emphasize the advantages of the nonconvex methods
over another convex approach to solving this problem in the differentially private setting. Experiments on synthetic and stylized data verify these results.