English
Related papers

Related papers: Adaptive Checkpoint Adjoint Method for Gradient Es…

200 papers

A neural network model of a differential equation, namely neural ODE, has enabled the learning of continuous-time dynamical systems and probabilistic distributions with high accuracy. The neural ODE uses the same network repeatedly during a…

Machine Learning · Computer Science 2021-10-20 Takashi Matsubara , Yuto Miyatake , Takaharu Yaguchi

Neural differential equations may be trained by backpropagating gradients via the adjoint method, which is another differential equation typically solved using an adaptive-step-size numerical differential equation solver. A proposed step is…

Machine Learning · Computer Science 2021-05-11 Patrick Kidger , Ricky T. Q. Chen , Terry Lyons

Neural ordinary differential equations (neural ODEs) have emerged as a novel network architecture that bridges dynamical systems and deep learning. However, the gradient obtained with the continuous adjoint method in the vanilla neural ODE…

Machine Learning · Computer Science 2023-06-12 Hong Zhang , Wenjun Zhao

This document, as the title stated, is meant to provide a vectorized implementation of adjoint dynamics calculation for Graph Convolutional Neural Ordinary Differential Equations (GCDE). The adjoint sensitivity method is the gradient…

Machine Learning · Computer Science 2022-09-16 Jack Cai

Neural ordinary differential equations (NODEs) presented a new paradigm to construct (continuous-time) neural networks. While showing several good characteristics in terms of the number of parameters and the flexibility in constructing…

Machine Learning · Computer Science 2021-06-01 Sheo Yon Jhin , Minju Jo , Taeyong Kong , Jinsung Jeon , Noseong Park

In this article we extend the adaptive cross approximation (ACA) method known for the efficient approximation of discretisations of integral operators to a block-adaptive version. While ACA is usually employed to assemble hierarchical…

Numerical Analysis · Mathematics 2019-05-07 M. Bauer , M. Bebendorf

Derivatives of differential equation solutions are commonly for parameter estimation, fitting neural differential equations, and as model diagnostics. However, with a litany of choices and a Cartesian product of potential methods, it can be…

Numerical Analysis · Computer Science 2021-07-21 Yingbo Ma , Vaibhav Dixit , Mike Innes , Xingjian Guo , Christopher Rackauckas

Neural Ordinary Differential Equations (Neural ODEs) represent a significant breakthrough in deep learning, promising to bridge the gap between machine learning and the rich theoretical frameworks developed in various mathematical fields…

Machine Learning · Computer Science 2024-09-24 Jaouad Dabounou

Robust federated learning aims to maintain reliable performance despite the presence of adversarial or misbehaving workers. While state-of-the-art (SOTA) robust distributed gradient descent (Robust-DGD) methods were proven theoretically…

Machine Learning · Computer Science 2025-05-12 Youssef Allouah , Rachid Guerraoui , Nirupam Gupta , Ahmed Jellouli , Geovani Rizk , John Stephan

We present and mathematically analyze an online adjoint algorithm for the optimization of partial differential equations (PDEs). Traditional adjoint algorithms would typically solve a new adjoint PDE at each optimization iteration, which…

Optimization and Control · Mathematics 2022-01-27 Justin Sirignano , Konstantinos Spiliopoulos

Meta-optics promises compact, high-performance imaging and color routing. However, designing high-performance structures is a high-dimensional optimization problem: mapping a desired optical output back to a physical 3D structure requires…

Machine Learning · Computer Science 2026-04-21 Chanik Kang , Hyewon Suk , Haejun Chung

This paper proposes an adaptive auxiliary task learning based approach for object counting problems. Unlike existing auxiliary task learning based methods, we develop an attention-enhanced adaptively shared backbone network to enable both…

Computer Vision and Pattern Recognition · Computer Science 2022-03-09 Yanda Meng , Joshua Bridge , Meng Wei , Yitian Zhao , Yihong Qiao , Xiaoyun Yang , Xiaowei Huang , Yalin Zheng

Designing an optimal deep neural network for a given task is important and challenging in many machine learning applications. To address this issue, we introduce a self-adaptive algorithm: the adaptive network enhancement (ANE) method,…

Numerical Analysis · Mathematics 2022-03-02 Zhiqiang Cai , Jingshuang Chen , Min Liu

A scaled conjugate gradient method that accelerates existing adaptive methods utilizing stochastic gradients is proposed for solving nonconvex optimization problems with deep neural networks. It is shown theoretically that, whether with…

Machine Learning · Computer Science 2024-12-17 Naoki Sato , Koshiro Izumi , Hideaki Iiduka

In this paper we consider the problem of decentralized (distributed) adaptive learning, where the aim of the network is to train the coefficients of a widely linear autoregressive moving average (ARMA) model by measurements collected by the…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-07-13 Azam Khalili , Reza G. Rahmati , Amir Rastegarnia , Wael M. Bazzi

Adaptive Computation (AC) has been shown to be effective in improving the efficiency of Open-Domain Question Answering (ODQA) systems. However, current AC approaches require tuning of all model parameters, and training state-of-the-art ODQA…

Computation and Language · Computer Science 2021-07-06 Yuxiang Wu , Pasquale Minervini , Pontus Stenetorp , Sebastian Riedel

Automated code generation allows for a separation between the development of a model, expressed via a domain specific language, and lower level implementation details. Algorithmic differentiation can be applied symbolically at the level of…

Programming Languages · Computer Science 2024-09-27 James R. Maddison

Receiver Operating Characteristic (ROC) curves are useful for evaluation in binary classification and changepoint detection, but difficult to use for learning since the Area Under the Curve (AUC) is piecewise constant (gradient zero almost…

Machine Learning · Computer Science 2024-10-14 Jadon Fowler , Toby Dylan Hocking

This paper presents a new functionality of the Automatic Differentiation (AD) tool Tapenade. Tapenade generates adjoint codes which are widely used for optimization or inverse problems. Unfortunately, for large applications the adjoint code…

Data Structures and Algorithms · Computer Science 2007-05-23 Laurent Hascoet , Mauricio Araya-Polo

In the paper, we propose a class of faster adaptive Gradient Descent Ascent (GDA) methods for solving the nonconvex-strongly-concave minimax problems by using the unified adaptive matrices, which include almost all existing coordinate-wise…

Optimization and Control · Mathematics 2023-02-22 Feihu Huang , Xidong Wu , Zhengmian Hu
‹ Prev 1 2 3 10 Next ›