English
Related papers

Related papers: Moonwalk: Inverse-Forward Differentiation

200 papers

Running backpropagation end to end on large neural networks is fraught with difficulties like vanishing gradients and degradation. In this paper we present an alternative architecture composed of many small neural networks that interact…

Machine Learning · Computer Science 2024-12-10 Stephen Pasteris , Chris Hicks , Vasilios Mavroudis

Deep-predictive-coding networks (DPCNs) are hierarchical, generative models. They rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial…

Artificial Intelligence · Computer Science 2021-09-27 Isaac J. Sledge , Jose C. Principe

Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of these solvers is zero or undefined, therefore a meaningful…

Machine Learning · Computer Science 2024-12-16 Subham Sekhar Sahoo , Anselm Paulus , Marin Vlastelica , Vít Musil , Volodymyr Kuleshov , Georg Martius

The growing size of datasets and deep learning models has made faster and memory-efficient training crucial. Reversible transformers have recently been introduced as an exciting new method for extremely memory-efficient training, but they…

Machine Learning · Computer Science 2023-06-16 Tyler Zhu , Karttikeya Mangalam

Finding the optimal hyperparameters of a model can be cast as a bilevel optimization problem, typically solved using zero-order techniques. In this work we study first-order methods when the inner optimization problem is convex but…

On-device fine-tuning enables privacy-preserving personalization of large language models, but mobile devices impose severe memory constraints, typically 6--12GB shared across all workloads. Existing approaches force a trade-off between…

Machine Learning · Computer Science 2026-02-16 Juneyoung Park , Yuri Hong , Seongwan Kim , Jaeho Lee

Integrating hard constraints into deep learning is essential for safety-critical systems. Yet existing constructive layers that project predictions onto constraint boundaries face a fundamental bottleneck: gradient saturation. By collapsing…

Machine Learning · Computer Science 2026-02-04 Philipp J. Schneider , Daniel Kuhn

In this paper, we provide an in-depth study of Stochastic Backpropagation (SBP) when training deep neural networks for standard image classification and object detection tasks. During backward propagation, SBP calculates the gradients by…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Jun Fang , Mingze Xu , Hao Chen , Bing Shuai , Zhuowen Tu , Joseph Tighe

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Feng Cheng , Mingze Xu , Yuanjun Xiong , Hao Chen , Xinyu Li , Wei Li , Wei Xia

Backpropagation (BP) is widely used for calculating gradients in deep neural networks (DNNs). Applied often along with stochastic gradient descent (SGD) or its variants, BP is considered as a de-facto choice in a variety of machine learning…

Machine Learning · Computer Science 2024-01-11 Ziang Li , Yiwen Guo , Haodi Liu , Changshui Zhang

The success of modern deep learning hinges on the ability to train neural networks at scale. Through clever reuse of intermediate information, backpropagation facilitates training through gradient computation at a total cost roughly…

Backpropagation of error (backprop) is a powerful algorithm for training machine learning architectures through end-to-end differentiation. However, backprop is often criticised for lacking biological plausibility. Recently, it has been…

Machine Learning · Computer Science 2020-10-07 Beren Millidge , Alexander Tschantz , Christopher L. Buckley

Computing the loss gradient via backpropagation consumes considerable energy during deep learning (DL) model training. In this paper, we propose a novel approach to efficiently compute DL models' gradients to mitigate the substantial energy…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Challapalli Phanindra Revanth , Sumohana S. Channappayya , C Krishna Mohan

Learning expressive probabilistic models correctly describing the data is a ubiquitous problem in machine learning. A popular approach for solving it is mapping the observations into a representation space with a simple joint distribution,…

Machine Learning · Statistics 2020-10-28 Luigi Gresele , Giancarlo Fissore , Adrián Javaloy , Bernhard Schölkopf , Aapo Hyvärinen

The scaling of neural networks with increasing data and model sizes necessitates the development of more efficient deep learning algorithms. A significant challenge in neural network training is the memory footprint associated with…

Machine Learning · Computer Science 2024-10-08 Georgii Novikov , Ivan Oseledets

Many applications of deep learning for image generation use perceptual losses for either training or fine-tuning of the generator networks. The use of perceptual loss however incurs repeated forward-backward passes in a large image…

Machine Learning · Computer Science 2021-05-06 Dmitry Nikulin , Roman Suvorov , Aleksei Ivakhnenko , Victor Lempitsky

Backpropagation is inherently sequential across depth, creating an $O(K)$-deep dependency chain that bottlenecks parallel training. While parallel-scan formulations theoretically reduce this depth to $O(\log K)$, they are computationally…

Machine Learning · Computer Science 2026-05-12 Shaun Christopher Lee , Sangeetha Abdu Jyothi

The brain cortex, which processes visual, auditory and sensory data in the brain, is known to have many recurrent connections within its layers and from higher to lower layers. But, in the case of machine learning with neural networks, it…

Machine Learning · Computer Science 2020-10-22 Sebastian Sanokowski

Understanding why gradient-based training in deep networks exhibits strong implicit bias remains challenging, in part because tractable singular-value dynamics are typically available only for balanced deep linear models. We propose an…

Machine Learning · Computer Science 2026-02-17 Nathanaël Haas , François Gatine , Augustin M Cosse , Zied Bouraoui

The study of Newton's method in complex-valued neural networks faces many difficulties. In this paper, we derive Newton's method backpropagation algorithms for complex-valued holomorphic multilayer perceptrons, and investigate the…

Complex Variables · Mathematics 2014-06-23 Diana Thomson La Corte , Yi Ming Zou
‹ Prev 1 3 4 5 6 7 10 Next ›