English
Related papers

Related papers: Gradients are Not All You Need

200 papers

We consider time-periodically perturbed 1D Hamiltonian systems possessing one or more separatrices. If the perturbation is weak, then the separatrix chaos is most developed when the perturbation frequency lies in the logarithmically small…

Chaotic Dynamics · Physics 2015-05-13 S. M. Soskin , R. Mannella , O. M. Yevtushenko , I. A. Khovanov , P. V. E. McClintock

Dynamical networks are important models for the behaviour of complex systems, modelling physical, biological and societal systems, including the brain, food webs, epidemic disease in populations, power grids and many other. Such dynamical…

Chaotic Dynamics · Physics 2017-03-27 Deniz Eroglu , Jeroen Lamb , Tiago Pereira

Deep neural networks are notorious for defying theoretical treatment. However, when the number of parameters in each layer tends to infinity, the network function is a Gaussian process (GP) and quantitatively predictive description is…

Machine Learning · Computer Science 2023-10-09 Darshil Doshi , Tianyu He , Andrey Gromov

Noise on quantum devices is much more complex than it is commonly given credit. Far from usual models of decoherence, nearly all quantum devices are plagued both by a continuum of environments and temporal instabilities. These induce noisy…

Quantum Physics · Physics 2025-08-27 Gregory A. L. White , Petar Jurcevic , Charles D. Hill , Kavan Modi

The human brain is the gold standard of adaptive learning. It not only can learn and benefit from experience, but also can adapt to new situations. In contrast, deep neural networks only learn one sophisticated but fixed mapping from inputs…

Computer Vision and Pattern Recognition · Computer Science 2021-03-18 Shixian Wen , Amanda Rios , Yunhao Ge , Laurent Itti

We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad…

Design of reliable systems must guarantee stability against input perturbations. In machine learning, such guarantee entails preventing overfitting and ensuring robustness of models against corruption of input data. In order to maximize…

Machine Learning · Statistics 2019-08-08 Judy Hoffman , Daniel A. Roberts , Sho Yaida

This paper is the second in a series of two, and describes the current state of the art in modelling and prediction of chaotic time series. Sampled data from deterministic non-linear systems may look stochastic when analysed with linear…

chao-dyn · Physics 2008-02-03 Bjoern Lillekjendlie , Dimitris Kugiumtzis , Nils Christophersen

Iterative optimization is central to modern artificial intelligence (AI) and provides a crucial framework for understanding adaptive systems. This review provides a unified perspective on this subject, bridging classic theory with neural…

Machine Learning · Computer Science 2025-10-22 Jesús García Fernández , Nasir Ahmad , Marcel van Gerven

The expectation that quantum computation might bring performance advantages in machine learning algorithms motivates the work on the quantum versions of artificial neural networks. In this study, we analyze the learning dynamics of a…

Quantum Physics · Physics 2023-10-17 Ufuk Korkmaz , Deniz Türkpençe

It has been observed that neural networks perform poorly when the data or tasks are presented sequentially. Unlike humans, neural networks suffer greatly from catastrophic forgetting, making it impossible to perform life-long learning. To…

Machine Learning · Computer Science 2023-01-31 Longhui Yu , Tianyang Hu , Lanqing Hong , Zhen Liu , Adrian Weller , Weiyang Liu

Cascading failure is a potentially devastating process that spreads on real-world complex networks and can impact the integrity of wide-ranging infrastructures, natural systems, and societal cohesiveness. One of the essential features that…

Stochastic variational Bayes algorithms have become very popular in the machine learning literature, particularly in the context of nonparametric Bayesian inference. These algorithms replace the true but intractable posterior distribution…

Methodology · Statistics 2024-10-04 Pedro Regueiro , Abel Rodríguez , Juan Sosa

Selective classifiers improve model reliability by abstaining on inputs the model deems uncertain. However, few practical approaches achieve the gold-standard performance of a perfect-ordering oracle that accepts examples exactly in order…

Machine Learning · Computer Science 2025-10-27 Stephan Rabanser , Nicolas Papernot

The choice of batch-size in a stochastic optimization algorithm plays a substantial role for both optimization and generalization. Increasing the batch-size used typically improves optimization but degrades generalization. To address the…

Machine Learning · Computer Science 2020-03-03 Yeming Wen , Kevin Luk , Maxime Gazeau , Guodong Zhang , Harris Chan , Jimmy Ba

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

Non-convex optimization problems are challenging to solve; the success and computational expense of a gradient descent algorithm or variant depend heavily on the initialization strategy. Often, either random initialization is used or…

Machine Learning · Computer Science 2020-12-23 Kartik Ahuja , Amit Dhurandhar , Kush R. Varshney

A plethora of modern machine learning tasks require the utilization of large-scale distributed clusters as a critical component of the training pipeline. However, abnormal Byzantine behavior of the worker nodes can derail the training and…

Machine Learning · Computer Science 2023-05-16 Konstantinos Konstantinidis , Namrata Vaswani , Aditya Ramamoorthy

Ordinary differential equations that model technical systems often contain states, that are considered dangerous for the system. A trajectory that reaches such a state usually indicates a flaw in the design. In this paper, we present and…

Optimization and Control · Mathematics 2016-10-05 Jan Kuratko , Stefan Ratschan

Learning rules -- prescriptions for updating model parameters to improve performance -- are typically assumed rather than derived. Why do some learning rules work better than others, and under what assumptions can a given rule be considered…

Machine Learning · Computer Science 2025-11-03 John J. Vastola , Samuel J. Gershman , Kanaka Rajan