17 accepted papers
We study the sparse spiked Wigner model, where the goal is to recover an $s$-sparse unit vector $\symbfit{u} \in \mathbb{R}^d$ from a noisy observation $\symbfit{Y} = \beta \symbfit{u} \symbfit{u}^\top + \symbfit{W}$. While the information-theoretic threshold is $\beta = \widetilde{\Omega}(\sqrt{s})…
Spectrally sparse signal reconstruction arises in a wide range of applications and can be formulated as a low-rank Hankel matrix completion problem. We develop a Jacobi-preconditioned gradient descent method that preserves the low per-iteration complexity of first-order algorithms while achieving li…
Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirical success, CFG relies on a heuristic linear extrapolation that is often sensitive to the guidance scale. In this work, we provide a principled interpretation …
Large tensor learning algorithms are typically computationally expensive and require storing a vast amount of data. In this paper, we propose a unified online Riemannian gradient descent (oRGrad) algorithm for tensor learning, which is computationally efficient, consumes much less memory, and can ha…
We study the problem of recovering an unknown $d_1 \times d_2$ rank-$r$ matrix from $m$ random linear measurements. Convex methods achieve the optimal sample complexity $m = \Omega(r(d_1 + d_2))$ but are computationally expensive. Non-convex approaches, while more computationally efficient, often re
We explore the single-spiked covariance model within the context of sparse principal component analysis (PCA), which aims to recover a sparse unit vector from noisy samples. From an information-theoretic perspective, $O(k \log p)$ observations are sufficient to recover a $k$-sparse $p$-dimensional v…
Finding low-rank matrix weights is a key technique for addressing the high memory usage and computational demands of large models. Most existing algorithms rely on the factorization of the low-rank matrix weights, which is non-unique and redundant. Their convergence is slow especially when the targe…
Tensors play a crucial role in numerous scientific and engineering fields. This paper addresses the low-multilinear-rank tensor completion problem, a fundamental task in tensor-related applications. By exploiting the manifold structure inherent to the fixed-multilinear-rank tensor set, we introduce…
We study the sparse phase retrieval problem, which seeks to recover a sparse signal from a limited set of magnitude-only measurements. In contrast to prevalent sparse phase retrieval algorithms that primarily use first-order methods, we propose an innovative second-order algorithm that employs a New…
The Bures-Wasserstein (BW) gradient descent method has gained considerable attention in various domains, including Gaussian barycenter, matrix recovery and variational inference problems, due to its alignment with the Wasserstein geometry of normal distributions. Despite its popularity, existing con…
Efficiently learning equilibria with large state and action spaces in general-sum Markov games while overcoming the curse of multi-agency is a challenging problem. Recent works have attempted to solve this problem by employing independent linear function classes to approximate the marginal $Q$-value…
We study the problem of estimating precision matrices in Gaussian distributions that are multivariate totally positive of order two ($\mathrm{MTP}_2$). The precision matrix in such a distribution is an M-matrix. This problem can be formulated as a sign-constrained log-determinant program. Current al…
We study the spectral super-resolution problem, which concerns the construction of an undamped spectrally sparse signal and its frequencies from its partially revealed entries. We propose a nonconvex method composed of a Hankel-Toeplitz matrix factorization model and a gradient descent algorithm ter…
Removing undesired reflections from images taken through the glass is of great importance in computer vision. It serves as a means to enhance the image quality for aesthetic purposes as well as to preprocess images in machine learning and pattern recognition applications. We propose a convex model t…
We consider the problem of spectral compressed sensing in continuous domain, which aims to recover a 2-dimensional spectrally sparse signal from partially observed time samples. The signal is assumed to be a superposition of s complex sinusoids. We propose a semidefinite program for the 2D signal re…
We propose fast algorithms that speed up or improve the performance of recovering spectrally sparse signals from un-derdetermined measurements. Our algorithms are based on a non-convex approach of using alternating projected gradient descent for structured matrix recovery. We apply this approach to…
Characterizing the phase transitions of convex optimizations in recovering structured signals or data is of central importance in compressed sensing, machine learning and statistics. The phase transitions of many convex optimization signal recovery methods such as ℓ <sub xmlns:mml="http://www.w3.org…