English
Related papers

Related papers: Analog Physical Systems Can Exhibit Double Descent

200 papers

Deep networks are typically trained with many more parameters than the size of the training dataset. Recent empirical evidence indicates that the practice of overparameterization not only benefits training large models, but also assists -…

Machine Learning · Computer Science 2020-12-17 Xiangyu Chang , Yingcong Li , Samet Oymak , Christos Thrampoulidis

A digital twin is a computer model that represents an individual, for example, a component, a patient or a process. In many situations, we want to gain knowledge about an individual from its data while incorporating imperfect physical…

Machine Learning · Statistics 2023-05-03 Michail Spitieris , Ingelin Steinsland

The Backprop algorithm for learning in neural networks utilizes two mechanisms: first, stochastic gradient descent and second, initialization with small random weights, where the latter is essential to the effectiveness of the former. We…

Machine Learning · Computer Science 2022-05-06 Shibhansh Dohare , Richard S. Sutton , A. Rupam Mahmood

Backpropagation with gradient descent is a common optimization strategy employed by most neural network architectures in machine learning. However, finding optimal hyperparameters to guide training has proven challenging. While it is widely…

Machine Learning · Computer Science 2026-05-20 Vy Bui , Hang Yu , Karthik Kantipudi , Ziv Yaniv , Stefan Jaeger

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

Despite their massive success, training successful deep neural networks still largely relies on experimentally choosing an architecture, hyper-parameters, initialization, and training mechanism. In this work, we focus on determining the…

Machine Learning · Computer Science 2021-11-29 Umangi Jain , Harish G. Ramaswamy

A Physics-Augmented Neural network is trained to model a hyperelastic behavior. The dataset used for the training, validation, and test are displacement-force couples obtained from two experiments on a rubber-like material. One experiment…

Computational Engineering, Finance, and Science · Computer Science 2024-10-23 Clément Jailin , Antoine Benady , Emmanuel Baranger

Physical networks, such as biological neural networks, can learn desired functions without a central processor, using local learning rules in space and time to learn in a fully distributed manner. Learning approaches such as equilibrium…

Disordered Systems and Neural Networks · Physics 2022-05-17 Menachem Stern , Sam Dillavou , Marc Z. Miskin , Douglas J. Durian , Andrea J. Liu

The success of deep learning in the computer vision and natural language processing communities can be attributed to training of very deep neural networks with millions or billions of parameters which can then be trained with massive…

Machine Learning · Computer Science 2021-02-17 Kei Ota , Devesh K. Jha , Asako Kanezaki

Large-scale foundation models for scientific machine learning adapt to physical settings unseen during training, such as zero-shot transfer between turbulent scales. This phenomenon, in-context learning, challenges conventional…

Machine Learning · Computer Science 2026-04-14 Anthony Bao , Jeffrey Lai , William Gilpin

We propose a novel method that makes use of deep neural networks and gradient decent to perform automated design on complex real world engineering tasks. Our approach works by training a neural network to mimic the fitness function of a…

Machine Learning · Statistics 2017-10-31 Oliver Hennigh

Machine-learning systems such as self-driving cars or virtual assistants are composed of a large number of machine-learning models that recognize image content, transcribe speech, analyze natural language, infer preferences, rank options,…

Machine Learning · Computer Science 2021-06-02 Ruihan Wu , Chuan Guo , Awni Hannun , Laurens van der Maaten

Farquhar et al. [2021] show that correcting for active learning bias with underparameterised models leads to improved downstream performance. For overparameterised models such as NNs, however, correction leads either to decreased or…

Machine Learning · Computer Science 2021-12-15 Chelsea Murray , James U. Allingham , Javier Antorán , José Miguel Hernández-Lobato

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…

Machine Learning · Computer Science 2019-01-23 Shaeke Salman , Xiuwen Liu

Bilevel optimization is a central tool in machine learning for high-dimensional hyperparameter tuning. Its applications are vast; for instance, in imaging it can be used for learning data-adaptive regularizers and optimizing forward…

Optimization and Control · Mathematics 2025-11-11 Mohammad Sadegh Salehi , Subhadip Mukherjee , Lindon Roberts , Matthias J. Ehrhardt

Data scarcity drives the need for more sample-efficient large language models. In this work, we use the double descent phenomenon to holistically compare the sample efficiency of discrete diffusion and autoregressive models. We show that…

Machine Learning · Computer Science 2025-09-30 Ahmad Fraij , Sam Dauncey

Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of…

The evolution and growing automation of collaborative robots introduce more complexity and unpredictability to systems, highlighting the crucial need for robot's adaptability and flexibility to address the increasing complexities of their…

Robotics · Computer Science 2024-03-21 Yuzhu Sun , Mien Van , Stephen McIlvanna , Nguyen Minh Nhat , Kabirat Olayemi , Jack Close , Seán McLoone

Most investigations into double descent have focused on supervised models while the few works studying self-supervised settings find a surprising lack of the phenomenon. These results imply that double descent may not exist in…

Machine Learning · Computer Science 2023-07-18 Alisia Lupidi , Yonatan Gideoni , Dulhan Jayalath