English
Related papers

Related papers: Continuous Deep Equilibrium Models: Training Neura…

200 papers

Stability of recurrent models is closely linked with trainability, generalizability and in some applications, safety. Methods that train stable recurrent neural networks, however, do so at a significant cost to expressibility. We propose an…

Machine Learning · Computer Science 2019-12-24 Max Revay , Ian R. Manchester

Deep Equilibrium (DEQ) Models, an emerging class of implicit models that maps inputs to fixed points of neural networks, are of growing interest in the deep learning community. However, training and applying DEQ models is currently done in…

Machine Learning · Computer Science 2023-10-31 Zhengyang Geng , J. Zico Kolter

We introduce economical versions of standard implicit ODE solvers that are specifically tailored for the efficient and accurate simulation of neural networks. These reformulations allow to achieve a significant increase in the efficiency of…

Numerical Analysis · Mathematics 2025-06-12 Luca Bonaventura , Soledad Fernández-García , Macarena Gómez-Mármol

High-order discretizations of partial differential equations (PDEs) necessitate high-order time integration schemes capable of handling both stiff and nonstiff operators in an efficient manner. Implicit-explicit (IMEX) integration based on…

Numerical Analysis · Mathematics 2022-01-19 Steven Roberts , Arash Sarshar , Adrian Sandu

Deep neural networks have long training and processing times. Early exits added to neural networks allow the network to make early predictions using intermediate activations in the network in time-sensitive applications. However, early…

Machine Learning · Computer Science 2022-12-27 Devdhar Patel , Hava Siegelmann

In this paper, we introduce an efficient backpropagation scheme for non-constrained implicit functions. These functions are parametrized by a set of learnable weights and may optionally depend on some input; making them perfectly suitable…

Machine Learning · Computer Science 2020-11-17 Andreas Look , Simona Doneva , Melih Kandemir , Rainer Gemulla , Jan Peters

Deep equilibrium networks (DEQs) are a new class of models that eschews traditional depth in favor of finding the fixed point of a single nonlinear layer. These models have been shown to achieve performance competitive with the…

Machine Learning · Computer Science 2021-06-29 Shaojie Bai , Vladlen Koltun , J. Zico Kolter

Neural Ordinary Differential Equations (Neural ODEs) represent continuous-time dynamics with neural networks, offering advancements for modeling and control tasks. However, training Neural ODEs requires solving differential equations at…

Machine Learning · Computer Science 2025-02-24 Mariia Shapovalova , Calvin Tsay

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

Machine Learning · Computer Science 2023-01-03 Michael Chang , Thomas L. Griffiths , Sergey Levine

Implicit neural networks are a general class of learning models that replace the layers in traditional feedforward models with implicit algebraic equations. Compared to traditional learning models, implicit networks offer competitive…

Machine Learning · Computer Science 2021-12-13 Saber Jafarpour , Matthew Abate , Alexander Davydov , Francesco Bullo , Samuel Coogan

In conventional formulations of multilayer feedforward neural networks, the individual layers are customarily defined by explicit functions. In this paper we demonstrate that defining individual layers in a neural network \emph{implicitly}…

Computer Vision and Pattern Recognition · Computer Science 2020-06-04 Qianggong Zhang , Yanyang Gu , Michalkiewicz Mateusz , Mahsa Baktashmotlagh , Anders Eriksson

Rapidly developing machine learning methods has stimulated research interest in computationally reconstructing differential equations (DEs) from observational data which may provide additional insight into underlying causative mechanisms.…

Machine Learning · Computer Science 2026-05-12 Mingtao Xia , Xiangting Li , Qijing Shen , Tom Chou

Learning models of dynamical systems with external inputs, which may be, for example, nonsmooth or piecewise, is crucial for studying complex phenomena and predicting future state evolution, which is essential for applications such as…

Machine Learning · Computer Science 2025-04-16 Zhaoyi Li , Wenjie Mei , Ke Yu , Yang Bai , Shihua Li

Model depth is a double-edged sword in deep learning: deeper models achieve higher accuracy but require higher computational cost. To efficiently train models at scale, an effective strategy is the progressive training, which scales up…

Machine Learning · Computer Science 2025-11-10 Zhiqi Bu

In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that…

Machine Learning · Computer Science 2015-11-24 Diogo Almeida , Nate Sauder

Advances in differentiable numerical integrators have enabled the use of gradient descent techniques to learn ordinary differential equations (ODEs). In the context of machine learning, differentiable solvers are central for Neural ODEs…

Machine Learning · Computer Science 2021-07-06 Weiming Zhi , Tin Lai , Lionel Ott , Edwin V. Bonilla , Fabio Ramos

In this work, we introduce a self-adaptive implicit-explicit (IMEX) time integration scheme, named IMEX-RB, for the numerical integration of systems of ordinary differential equations (ODEs), arising from spatial discretizations of partial…

Numerical Analysis · Mathematics 2025-07-28 Micol Bassanini , Simone Deparis , Francesco Sala , Riccardo Tenderini

Gradient descent can be surprisingly good at optimizing deep neural networks without overfitting and without explicit regularization. We find that the discrete steps of gradient descent implicitly regularize models by penalizing gradient…

Machine Learning · Computer Science 2022-07-20 David G. T. Barrett , Benoit Dherin

The Adam optimizer, often used in Machine Learning for neural network training, corresponds to an underlying ordinary differential equation (ODE) in the limit of very small learning rates. This work shows that the classical Adam algorithm…

Computational Engineering, Finance, and Science · Computer Science 2024-09-17 Abhinab Bhattacharjee , Andrey A. Popov , Arash Sarshar , Adrian Sandu

Fast and accurate solutions of time-dependent partial differential equations (PDEs) are of pivotal interest to many research fields, including physics, engineering, and biology. Generally, implicit/semi-implicit schemes are preferred over…