Related papers: Stochastic parallel gradient descent based adaptiv…
We provide the first theoretical analysis on the convergence rate of the asynchronous stochastic variance reduced gradient (SVRG) descent algorithm on non-convex optimization. Recent studies have shown that the asynchronous stochastic…
We propose the application of coronagraphic techniques to the spectroscopic direct detection of exoplanets via the Doppler shift of planetary molecular lines. Even for an unresolved close-in planetary system, we show that the combination of…
We aim to make stochastic gradient descent (SGD) adaptive to (i) the noise $\sigma^2$ in the stochastic gradients and (ii) problem-dependent constants. When minimizing smooth, strongly-convex functions with condition number $\kappa$, we…
Distributed stochastic gradient descent (SGD) with gradient compression has become a popular communication-efficient solution for accelerating distributed learning. One commonly used method for gradient compression is Top-K sparsification,…
The development of adaptive optics (AO) played a major role in modern astronomy over the last three decades. By compensating for the atmospheric turbulence, these systems enable to reach the diffraction limit on large telescopes. In this…
The PIAA is a now well demonstrated high contrast technique that uses an intermediate remapping of the pupil for high contrast coronagraphy (apodization), before restoring it to recover classical imaging capabilities. This paper presents…
Adaptive optics (AO) has revolutionized imaging in {fields} from astronomy to microscopy by correcting optical aberrations. In label-free microscopes, however, conventional AO faces limitations due to the absence of guidestar and the need…
Proximal gradient algorithms (PGA), while foundational for inverse problems like image reconstruction, often yield unstable convergence and suboptimal solutions by violating the critical non-negativity constraint. We identify the gradient…
A popular method of force-directed graph drawing is multidimensional scaling using graph-theoretic distances as input. We present an algorithm to minimize its energy function, known as stress, by using stochastic gradient descent (SGD) to…
Compressed Stochastic Gradient Descent (SGD) algorithms have been recently proposed to address the communication bottleneck in distributed and decentralized optimization problems, such as those that arise in federated machine learning.…
The exoplanetary science through direct imaging and spectroscopy will largely expand with the forthcoming development of new instruments at the VLT (SPHERE), Gemini (GPI), Subaru (HiCIAO), and Palomar (Project 1640) observatories. All these…
Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent…
The Projected Gradient Descent (PGD) algorithm is a widely used and efficient first-order method for solving constrained optimization problems due to its simplicity and scalability in large design spaces. Building on recent advancements in…
Coronagraphs of the apodized pupil and shaped pupil varieties use the Fraunhofer diffraction properties of amplitude masks to create regions of high contrast in the vicinity of a target star. Here we present a hybrid coronagraph…
We summarize the theory of coronagraphic optics, and identify a dimensionless fine-tuning parameter, F, which we use to describe the Lyot stop size in the natural units of the coronagraphic optical train and the observing wavelength. We…
Electron cryomicroscopy (cryo-EM) is an imaging technique widely used in structural biology to determine the three-dimensional structure of biological molecules from noisy two-dimensional projections with unknown orientations. As the…
Optical Coherence Tomography (OCT) is a widely used non-invasive imaging technique that provides detailed three-dimensional views of the retina, which are essential for the early and accurate diagnosis of ocular diseases. Consequently, OCT…
Stochastic gradient descent (SGD) algorithm is an effective learning strategy to build a latent factor analysis (LFA) model on a high-dimensional and incomplete (HDI) matrix. A particle swarm optimization (PSO) algorithm is commonly adopted…
The major source of noise in high-contrast imaging is the presence of slowly evolving speckles that do not average with time. The temporal stability of the point-spread-function (PSF) is therefore critical to reach a high contrast with…
We introduce data structures for solving robust regression through stochastic gradient descent (SGD) by sampling gradients with probability proportional to their norm, i.e., importance sampling. Although SGD is widely used for large scale…