English
Related papers

Related papers: Local Loss Optimization in the Infinite Width: Sta…

200 papers

The biological implausibility of backpropagation (BP) has motivated many alternative, brain-inspired algorithms that attempt to rely only on local information, such as predictive coding (PC) and equilibrium propagation. However, these…

Machine Learning · Computer Science 2025-12-01 Francesco Innocenti , El Mehdi Achour , Christopher L. Buckley

In this paper we study a constraint-based representation of neural network architectures. We cast the learning problem in the Lagrangian framework and we investigate a simple optimization procedure that is well suited to fulfil the…

Machine Learning · Computer Science 2020-04-20 Giuseppe Marra , Matteo Tiezzi , Stefano Melacci , Alessandro Betti , Marco Maggini , Marco Gori

Backpropagation (BP) of errors is the backbone training algorithm for artificial neural networks (ANNs). It updates network weights through gradient descent to minimize a loss function representing the mismatch between predictions and…

Machine Learning · Statistics 2025-08-13 Davide Casnici , Charlotte Frenkel , Justin Dauwels

Predictive coding (PC) is an influential theory of information processing in the brain, providing a biologically plausible alternative to backpropagation. It is motivated in terms of Bayesian inference, as hidden states and parameters are…

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

This paper presents a unified analysis framework that captures recent advances in the study of local-optimality characterizations for codes on graphs. These local-optimality characterizations are based on combinatorial structures embedded…

Information Theory · Computer Science 2012-08-15 Guy Even , Nissim Halabi

Backpropagation (BP) has been a successful optimization technique for deep learning models. However, its limitations, such as backward- and update-locking, and its biological implausibility, hinder the concurrent updating of layers and do…

Machine Learning · Computer Science 2023-12-22 Anzhe Cheng , Zhenkun Wang , Chenzhong Yin , Mingxi Cheng , Heng Ping , Xiongye Xiao , Shahin Nazarian , Paul Bogdan

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

Deeper modern architectures are costly to train, making hyperparameter transfer preferable to expensive repeated tuning. Maximal Update Parametrization ($\mu$P) helps explain why many hyperparameters transfer across width. Yet depth scaling…

Machine Learning · Computer Science 2026-02-10 Shenxi Wu , Haosong Zhang , Xingjian Ma , Shirui Bian , Yichi Zhang , Xi Chen , Wei Lin

To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, the nonlinear and compositional structure of these models…

Machine Learning · Computer Science 2021-12-21 Karl Hajjar , Lénaïc Chizat , Christophe Giraud

Predictive coding networks (PCNs) are an influential model for information processing in the brain. They have appealing theoretical interpretations and offer a single mechanism that accounts for diverse perceptual phenomena of the brain. On…

Machine Learning · Computer Science 2021-03-08 Tommaso Salvatori , Yuhang Song , Thomas Lukasiewicz , Rafal Bogacz , Zhenghua Xu

We present the first theoretical framework that connects predictive coding (PC), a biologically inspired local learning rule, with the minimum description length (MDL) principle in deep networks. We prove that layerwise PC performs…

Machine Learning · Computer Science 2025-07-17 Benjamin Prada , Shion Matsumoto , Abdul Malik Zekri , Ankur Mali

By classifying infinite-width neural networks and identifying the *optimal* limit, Tensor Programs IV and V demonstrated a universal way, called $\mu$P, for *widthwise hyperparameter transfer*, i.e., predicting optimal hyperparameters of…

Neural and Evolutionary Computing · Computer Science 2023-10-13 Greg Yang , Dingli Yu , Chen Zhu , Soufiane Hayou

Training neural networks with reinforcement learning (RL) typically relies on backpropagation (BP), necessitating storage of activations from the forward pass for subsequent backward updates. Furthermore, backpropagating error signals…

Machine Learning · Computer Science 2025-07-16 Daniel Tanneberg

Distributed optimization often consists of two updating phases: local optimization and inter-node communication. Conventional approaches require working nodes to communicate with the server every one or few iterations to guarantee…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-06-17 Chi Zhang , Qianxiao Li

While over-parameterization is widely believed to be crucial for the success of optimization for the neural networks, most existing theories on over-parameterization do not fully explain the reason -- they either work in the Neural Tangent…

Machine Learning · Computer Science 2021-07-06 Mo Zhou , Rong Ge , Chi Jin

Transferring the optimal learning rate from small to large neural networks can enable efficient training at scales where hyperparameter tuning is otherwise prohibitively expensive. To this end, the Maximal Update Parameterization (muP)…

Machine Learning · Computer Science 2026-02-16 Atli Kosson , Jeremy Welborn , Yang Liu , Martin Jaggi , Xi Chen

The backpropagation of error algorithm used to train deep neural networks has been fundamental to the successes of deep learning. However, it requires sequential backward updates and non-local computations, which make it challenging to…

Neural and Evolutionary Computing · Computer Science 2022-02-22 Beren Millidge , Tommaso Salvatori , Yuhang Song , Rafal Bogacz , Thomas Lukasiewicz

Zero padding is often used in convolutional neural networks to prevent the feature map size from decreasing with each layer. However, recent studies have shown that zero padding promotes encoding of absolute positional information, which…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Kensuke Mukai , Takao Yamanaka

Predictive coding (PC) is a general theory of cortical function. The local, gradient-based learning rules found in one kind of PC model have recently been shown to closely approximate backpropagation. This finding suggests that this…

Neural and Evolutionary Computing · Computer Science 2021-12-09 Nick Alonso , Emre Neftci