English
Related papers

Related papers: Efficient Neural and Numerical Methods for High-Qu…

200 papers

We study the problem of learning a low-degree spherical polynomial of degree $k_0 = \Theta(1) \ge 1$ defined on the unit sphere in $\RR^d$ by training an over-parameterized two-layer neural network with augmented feature in this paper. Our…

Machine Learning · Statistics 2026-03-24 Yingzhen Yang , Ping Li

In distributed training of deep neural networks, people usually run Stochastic Gradient Descent (SGD) or its variants on each machine and communicate with other machines periodically. However, SGD might converge slowly in training some deep…

Machine Learning · Computer Science 2022-10-14 Mingrui Liu , Zhenxun Zhuang , Yunwei Lei , Chunyang Liao

First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks. Second-order methods, despite their better convergence rate, are rarely used in practice due to the…

Machine Learning · Computer Science 2019-09-26 Tianle Cai , Ruiqi Gao , Jikai Hou , Siyu Chen , Dong Wang , Di He , Zhihua Zhang , Liwei Wang

Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation workers. However, by nature, workers need to frequently…

Machine Learning · Computer Science 2018-02-21 Yusuke Tsuzuku , Hiroto Imachi , Takuya Akiba

This paper investigates whether sequence models can learn to perform numerical algorithms, e.g. gradient descent, on the fundamental problem of least squares. Our goal is to inherit two properties of standard algorithms from numerical…

Machine Learning · Computer Science 2025-03-18 Jerry Liu , Jessica Grogan , Owen Dugan , Ashish Rao , Simran Arora , Atri Rudra , Christopher Ré

Advances in numerical optimization have supported breakthroughs in several areas of signal processing. This paper focuses on the recent enhanced variants of the proximal gradient numerical optimization algorithm, which combine quasi-Newton…

Signal Processing · Electrical Eng. & Systems 2020-01-28 Niccolò Antonello , Lorenzo Stella , Panagiotis Patrinos , Toon van Waterschoot

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

Despite noise suppression being a mature area in signal processing, it remains highly dependent on fine tuning of estimator algorithms and parameters. In this paper, we demonstrate a hybrid DSP/deep learning approach to noise suppression. A…

Sound · Computer Science 2018-06-04 Jean-Marc Valin

This paper proposes an approach to the joint modeling of the short-time Fourier transform magnitude and phase spectrograms with a deep generative model. We assume that the magnitude follows a Gaussian distribution and the phase follows a…

Sound · Computer Science 2022-07-18 Aditya Arie Nugraha , Kouhei Sekiguchi , Kazuyoshi Yoshii

Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. However, one typically sets them using heuristic approaches…

Machine Learning · Computer Science 2025-12-05 Dravyansh Sharma

This paper presents a novel speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra by neural networks. The proposed model is a cascade of a residual convolutional network and a parallel estimation…

Sound · Computer Science 2023-02-17 Yang Ai , Zhen-Hua Ling

This paper develops and analyzes an online distributed proximal-gradient method (DPGM) for time-varying composite convex optimization problems. Each node of the network features a local cost that includes a smooth strongly convex function…

Optimization and Control · Mathematics 2024-05-07 Nicola Bastianello , Emiliano Dall'Anese

This paper presents a novel neural speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra. The proposed model is a cascade of a residual convolutional network and a parallel estimation…

Sound · Computer Science 2024-03-27 Yang Ai , Zhen-Hua Ling

We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first…

Optimization and Control · Mathematics 2016-02-25 Aymeric Dieuleveut , Nicolas Flammarion , Francis Bach

We consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function (comparator) in hindsight. Popular algorithms in this…

Machine Learning · Computer Science 2019-02-21 Michał Kempka , Wojciech Kotłowski , Manfred K. Warmuth

Currently, most speech processing techniques use magnitude spectrograms as front-end and are therefore by default discarding part of the signal: the phase. In order to overcome this limitation, we propose an end-to-end learning method for…

Sound · Computer Science 2018-02-01 Dario Rethage , Jordi Pons , Xavier Serra

Quantum machine learning and optimization are exciting new areas that have been brought forward by the breakthrough quantum algorithm of Harrow, Hassidim and Lloyd for solving systems of linear equations. The utility of {classical} linear…

Quantum Physics · Physics 2021-03-02 Iordanis Kerenidis , Anupam Prakash

This paper presents a novel phase reconstruction method (only from a given amplitude spectrogram) by combining a signal-processing-based approach and a deep neural network (DNN). To retrieve a time-domain signal from its amplitude…

Sound · Computer Science 2019-03-12 Yoshiki Masuyama , Kohei Yatabe , Yuma Koizumi , Yasuhiro Oikawa , Noboru Harada

Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-17 Jalal Abdulbaqi , Yue Gu , Ivan Marsic

Stochastic gradient methods for machine learning and optimization problems are usually analyzed assuming data points are sampled \emph{with} replacement. In practice, however, sampling \emph{without} replacement is very common, easier to…

Machine Learning · Computer Science 2016-10-18 Ohad Shamir