English
Related papers

Related papers: Noise-induced degeneration in online learning

200 papers

Traditional analyses of gradient descent optimization show that, when the largest eigenvalue of the loss Hessian - often referred to as the sharpness - is below a critical learning-rate threshold, then training is 'stable' and training loss…

Machine Learning · Computer Science 2024-12-24 Lawrence Wang , Stephen J. Roberts

Driven by the need to solve increasingly complex optimization problems in signal processing and machine learning, there has been increasing interest in understanding the behavior of gradient-descent algorithms in non-convex environments.…

Optimization and Control · Mathematics 2019-07-04 Stefan Vlaski , Ali H. Sayed

We analyze the effect of weak-noise-induced transitions on the dynamics of the FitzHugh-Nagumo neuron model in a bistable state consisting of a stable fixed point and a stable unforced limit cycle. Bifurcation and slow-fast analysis give…

Dynamical Systems · Mathematics 2017-06-02 Marius E. Yamakou , Jürgen Jost

The natural gradient allows for more efficient gradient descent by removing dependencies and biases inherent in a function's parameterization. Several papers present the topic thoroughly and precisely. It remains a very difficult idea to…

Machine Learning · Computer Science 2012-05-10 Jascha Sohl-Dickstein

Variational quantum algorithms rely on gradient based optimization to iteratively minimize a cost function evaluated by measuring output(s) of a quantum processor. A barren plateau is the phenomenon of exponentially vanishing gradients in…

Quantum Physics · Physics 2021-10-26 Alexey Uvarov , Jacob Biamonte

Many applications in machine learning or signal processing involve nonsmooth optimization problems. This nonsmoothness brings a low-dimensional structure to the optimal solutions. In this paper, we propose a randomized proximal gradient…

Optimization and Control · Mathematics 2020-04-29 Dmitry Grishchenko , Franck Iutzeler , Jérôme Malick

We systematically investigate the interplay of disorder and time-homogeneous collisional noise in shaping the transport dynamics of an anisotropic XXZ spin chain. Using stochastic collision models to simulate interaction with the…

Quantum Physics · Physics 2025-12-30 Vittoria Stanzione , Alessandro Civolani , Jorge Yago Malo , Maria Luisa Chiofalo

Gradient-based optimization of neural differential equations and other parameterized dynamical systems fundamentally relies on the ability to differentiate numerical solutions with respect to model parameters. In stiff systems, it has been…

Machine Learning · Computer Science 2025-08-05 Colby Fronk , Linda Petzold

We investigate the influence of nonstationary 1/f^mu noise, produced by interacting defects, on a quantum two-level system. Adopting a simple phenomenological model for this noise we describe exactly the corresponding dephasing in various…

Mesoscale and Nanoscale Physics · Physics 2009-11-10 Josef Schriefl , Maxime Clusel , David Carpentier , Pascal Degiovanni

Nonlinear damping, the change in damping rate with the amplitude of oscillations plays an important role in many electrical, mechanical and even biological oscillators. In novel technologies such as carbon nanotubes, graphene membranes or…

Diffusion models (DMs) are a powerful generative framework that have attracted significant attention in recent years. However, the high computational cost of training DMs limits their practical applications. In this paper, we start with a…

Machine Learning · Computer Science 2024-04-12 Tianshuo Xu , Peng Mi , Ruilin Wang , Yingcong Chen

Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks under certain conditions, one step of gradient descent on the…

Machine Learning · Statistics 2025-04-11 Behrad Moniri , Donghwan Lee , Hamed Hassani , Edgar Dobriban

We study the complexity of training neural network models with one hidden nonlinear activation layer and an output weighted sum layer. We analyze Gradient Descent applied to learning a bounded target function on $n$ real-valued inputs. We…

Machine Learning · Computer Science 2019-05-28 Santosh Vempala , John Wilmes

This paper studies the stability of low-rank implicit regularization in perturbed deep matrix factorization, where the target matrix is corrupted by a noise matrix. We first derive sufficient spectral conditions under which gradient descent…

Optimization and Control · Mathematics 2026-05-28 Jingzhe Wang , Hung-Hsu Chou

Recursion is a fundamental concept in the design of filters and audio systems. In particular, artificial reverberation systems that use delay networks depend on recursive paths to control both echo density and the decay rate of modal…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-28 Gloria Dal Santo , Karolina Prawda , Sebastian J. Schlecht , Vesa Välimäki

An important challenge in quantum science is to fully understand the efficiency of energy flow in networks. Here we present a simple and intuitive explanation for the intriguing observation that optimally efficient networks are not purely…

Quantum Physics · Physics 2015-03-24 Ying Li , Filippo Caruso , Erik Gauger , Simon C. Benjamin

A law of large numbers for the empirical distribution of parameters of a one-layer artificial neural networks with sparse connectivity is derived for a simultaneously increasing number of both, neurons and training iterations of the…

Disordered Systems and Neural Networks · Physics 2021-12-13 Christian Hirsch , Matthias Neumann , Volker Schmidt

We theoretically describe how weak signals may be efficiently transmitted throughout more than one frequency range in noisy excitable media by kind of stochastic multiresonance. This serves us here to reinterpret recent experiments in…

Data Analysis, Statistics and Probability · Physics 2015-05-27 J. J. Torres , J. Marro , J. F. Mejias

In this paper, we focus on online representation learning in non-stationary environments which may require continuous adaptation of model architecture. We propose a novel online dictionary-learning (sparse-coding) framework which…

Machine Learning · Computer Science 2018-02-07 Sahil Garg , Irina Rish , Guillermo Cecchi , Aurelie Lozano

The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any…

Machine Learning · Statistics 2013-02-19 Tom Schaul , Sixin Zhang , Yann LeCun