English
Related papers

Related papers: Deep equilibrium networks are sensitive to initial…

200 papers

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM)…

Deep equilibrium models (DEQs), as a typical implicit neural network, have demonstrated remarkable success on various tasks. There is, however, a lack of theoretical understanding of the connections and differences between implicit DEQs and…

Machine Learning · Computer Science 2024-05-21 Zenan Ling , Longbo Li , Zhanbo Feng , Yixuan Zhang , Feng Zhou , Robert C. Qiu , Zhenyu Liao

Implicit models such as Deep Equilibrium Models (DEQs) have garnered significant attention in the community for their ability to train infinite layer models with elegant solution-finding procedures and constant memory footprint. However,…

Machine Learning · Computer Science 2023-10-23 Haobo Song , Soumajit Majumder , Tao Lin

Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly advancing these disciplines. However, neural Networks persistently face challenges related to…

Machine Learning · Computer Science 2025-10-14 Yongshuai Liu , Lianfang Wang , Kuilin Qin , Qinghua Zhang , Faqiang Wang , Li Cui , Jun Liu , Yuping Duan , Tieyong Zeng

Even though dense networks have lost importance today, they are still used as final logic elements. It could be shown that these dense networks can be simplified by the sparse graph interpretation. This in turn shows that the information…

Neural and Evolutionary Computing · Computer Science 2018-09-25 Thomas Pircher , Dominik Haspel , Eberhard Schlücker

Deep equilibrium (DEQ) models are widely recognized as a memory efficient alternative to standard neural networks, achieving state-of-the-art performance in language modeling and computer vision tasks. These models solve a fixed point…

Machine Learning · Computer Science 2024-06-25 Mateusz Gabor , Tomasz Piotrowski , Renato L. G. Cavalcante

The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance. Yet…

Machine Learning · Computer Science 2020-01-17 Wei Hu , Lechao Xiao , Jeffrey Pennington

Despite Deep Learning's (DL) empirical success, our theoretical understanding of its efficacy remains limited. One notable paradox is that while conventional wisdom discourages perfect data fitting, deep neural networks are designed to do…

Machine Learning · Computer Science 2024-02-06 Oria Gruber , Haim Avron

We propose a new class of implicit networks, the multiscale deep equilibrium model (MDEQ), suited to large-scale and highly hierarchical pattern recognition domains. An MDEQ directly solves for and backpropagates through the equilibrium…

Machine Learning · Computer Science 2020-11-25 Shaojie Bai , Vladlen Koltun , J. Zico Kolter

Deep neural networks are typically initialized with random weights, with variances chosen to facilitate signal propagation and stable gradients. It is also believed that diversity of features is an important property of these…

Machine Learning · Computer Science 2020-07-03 Yaniv Blumenfeld , Dar Gilboa , Daniel Soudry

Residual networks (ResNet) and weight normalization play an important role in various deep learning applications. However, parameter initialization strategies have not been studied previously for weight normalized networks and, in practice,…

Machine Learning · Statistics 2019-10-31 Devansh Arpit , Victor Campos , Yoshua Bengio

Principal Component Analysis (PCA) and its exponential family extensions have three components: observations, latents and parameters of a linear transformation. We consider a generalised setting where the canonical parameters of the…

Machine Learning · Computer Science 2022-11-14 Russell Tsuchida , Cheng Soon Ong

We show that deep learning models, and especially architectures like the Transformer, originally intended for natural language, can be trained on randomly generated datasets to predict to very high accuracy both the qualitative and…

Machine Learning · Computer Science 2021-12-08 François Charton , Amaury Hayat , Sean T. McQuade , Nathaniel J. Merrill , Benedetto Piccoli

In this work a novel, automated process for constructing and initializing deep feed-forward neural networks based on decision trees is presented. The proposed algorithm maps a collection of decision trees trained on the data into a…

Machine Learning · Computer Science 2018-07-04 K. D. Humbird , J. L. Peterson , R. G. McClarren

Deep Equilibrium Models (DEQs) replace a stack of explicit layers with a single operator whose fixed point defines the output, giving the expressive power of an arbitrarily deep network at the memory cost of a single layer. Quantum Deep…

Quantum Physics · Physics 2026-05-12 Pengyuan Xu , Tristan Zaborniak , Luis F. Rivera , Hausi A. Müller

A new design methodology for neural networks that is guided by traditional algorithm design is presented. To prove our point, we present two heuristics and demonstrate an algorithmic technique for incorporating additional weights in their…

Machine Learning · Computer Science 2018-06-07 Abhejit Rajagopal , Shivkumar Chandrasekaran , Hrushikesh N. Mhaskar

Deep neural networks (DNNs) form the backbone of almost every state-of-the-art technique in the fields such as computer vision, speech processing, and text analysis. The recent advances in computational technology have made the use of DNNs…

Machine Learning · Computer Science 2018-03-20 Saiprasad Koturwar , Shabbir Merchant

The statistical properties of deep neural networks (DNNs) at initialization play an important role to comprehend their trainability and the intrinsic architectural biases they possess before data exposure Well established mean field (MF)…

Machine Learning · Computer Science 2026-03-03 Alberto Bassi , Marco Baity-Jesi , Aurelien Lucchi , Carlo Albert , Emanuele Francazi

We develop a deep learning algorithm for constructing globally accurate approximations to functional rational expectations equilibria of dynamic stochastic economies in the sequence space. We use deep neural networks to parameterize key…

General Economics · Economics 2026-03-17 Marlon Azinovic-Yang , Jan Žemlička

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these…

Machine Learning · Computer Science 2018-11-16 Raghuram Mandyam Annasamy , Katia Sycara