It has been observed that the performances of many high-dimensional
esti...
The generalization performance of kernel ridge regression (KRR) exhibits...
We consider random matrices whose entries are obtained by applying a
(no...
We analyze the dynamics of a random sequential message passing algorithm...
Randomly perturbing networks during the training process is a commonly u...
This paper proposes a new algorithm, named Householder Dice (HD), for
si...
Transfer learning seeks to improve the generalization performance of a t...
We consider the phase retrieval problem, in which the observer wishes to...
We prove a universality theorem for learning with random features. Our r...
We study the problem of learning an unknown function using random featur...
Estimating a binary vector from noisy linear measurements is a prototypi...
We consider a commonly studied supervised classification of a synthetic
...
We consider a high-dimensional mixture of two Gaussians in the noisy reg...
In Generalized Linear Estimation (GLE) problems, we seek to estimate a s...
In sparse linear regression, the SLOPE estimator generalizes LASSO by
as...
We present the optimal design of a spectral method widely used to initia...
Substantial progress has been made recently on developing provably accur...
In a variety of fields, in particular those involving imaging and optics...
For many modern applications in science and engineering, data are collec...
We study algorithms for solving quadratic systems of equations based on
...
Despite the remarkable successes of generative adversarial networks (GAN...
We present a high-dimensional analysis of three popular algorithms, name...
We present a framework for analyzing the exact dynamics of a class of on...
We analyze the dynamics of an online algorithm for independent component...
We study a spectral initialization method that serves a key role in rece...
We propose an image representation scheme combining the local and nonloc...
Many patch-based image denoising algorithms can be formulated as applyin...
We propose a randomized version of the non-local means (NLM) algorithm f...