English
Related papers

Related papers: An Ode to an ODE

200 papers

The assignment flow is a smooth dynamical system that evolves on an elementary statistical manifold and performs contextual data labeling on a graph. We derive and introduce the linear assignment flow that evolves nonlinearly on the…

Numerical Analysis · Mathematics 2021-10-14 Alexander Zeilmann , Fabrizio Savarino , Stefania Petra , Christoph Schnörr

We propose Lie group embedded dynamical neural networks (LieEDNN) and the corresponding learning algorithms based on gradient descent and metric projection on smooth manifold, where we treat Lie group as an intrinsic representation for…

Machine Learning · Computer Science 2026-05-27 Tianwei Wang , Bryan Chen , Qian Zuo , Qiyue Xia , Xin Li , Wei Pang

Accelerated gradient descent iterations are widely used in optimization. It is known that, in the continuous-time limit, these iterations converge to a second-order differential equation which we refer to as the accelerated gradient flow.…

Optimization and Control · Mathematics 2020-06-16 Mohammad Farazmand

Gradient descent, or negative gradient flow, is a standard technique in optimization to find minima of functions. Many implementations of gradient descent rely on discretized versions, i.e., moving in the gradient direction for a set step…

Differential Geometry · Mathematics 2024-07-01 Dara Gold , Steven Rosenberg

Dissipative partial differential equations that exhibit chaotic dynamics tend to evolve to attractors that exist on finite-dimensional manifolds. We present a data-driven reduced order modeling method that capitalizes on this fact by…

Machine Learning · Computer Science 2022-07-20 Alec J. Linot , Michael D. Graham

Flow matching has emerged as a powerful framework for generative modeling, with recent empirical successes highlighting the effectiveness of signal-space prediction ($x$-prediction). In this work, we investigate the transfer of this…

Machine Learning · Computer Science 2026-05-05 Jiadong Hong , Lei Liu , Xinyu Bian , Wenjie Wang , Zhaoyang Zhang

In this work, we establish a frequency-domain framework for analyzing gradient-based algorithms in linear minimax optimization problems; specifically, our approach is based on the Z-transform, a powerful tool applied in Control Theory and…

Optimization and Control · Mathematics 2020-10-08 Ioannis Anagnostides , Paolo Penna

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Most machine learning methods are used as a black box for modelling. We may try to extract some knowledge from physics-based training methods, such as neural ODE (ordinary differential equation). Neural ODE has advantages like a possibly…

Machine Learning · Computer Science 2022-06-08 Yakov Golovanev , Alexander Hvatov

In Continual Learning settings, deep neural networks are prone to Catastrophic Forgetting. Orthogonal Gradient Descent was proposed to tackle the challenge. However, no theoretical guarantees have been proven yet. We present a theoretical…

Machine Learning · Statistics 2020-12-07 Mehdi Abbana Bennani , Thang Doan , Masashi Sugiyama

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Machine Learning · Computer Science 2026-05-15 Quanhao Li , Junqiu Yu , Kaixun Jiang , Yujie Wei , Zhen Xing , Pandeng Li , Ruihang Chu , Shiwei Zhang , Yu Liu , Zuxuan Wu

Pairwise learning refers to learning tasks where the loss function depends on a pair of instances. It instantiates many important machine learning tasks such as bipartite ranking and metric learning. A popular approach to handle streaming…

Machine Learning · Computer Science 2021-11-25 Zhenhuan Yang , Yunwen Lei , Puyu Wang , Tianbao Yang , Yiming Ying

Autoregressive next-step prediction models have become the de-facto standard for building data-driven neural solvers to forecast time-dependent partial differential equations (PDEs). Denoise training that is closely related to diffusion…

Machine Learning · Computer Science 2025-03-31 Zijie Li , Anthony Zhou , Amir Barati Farimani

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

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

Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existing approaches either lack clear convergence guarantees, or…

Machine Learning · Computer Science 2026-03-11 Hui Yang , Tao Ren , Jinyang Jiang , Wan Tian , Yijie Peng

Deep learning has achieved tremendous success by training increasingly large models, which are then compressed for practical deployment. We propose a drastically different approach to compact and optimal deep learning: We decouple the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-28 Jiayun Wang , Yubei Chen , Stella X. Yu , Brian Cheung , Yann LeCun

A major challenge in the training of recurrent neural networks is the so-called vanishing or exploding gradient problem. The use of a norm-preserving transition operator can address this issue, but parametrization is challenging. In this…

Machine Learning · Statistics 2017-01-11 Stephanie L. Hyland , Gunnar Rätsch

Topology Optimization (TO) provides a systematic approach for obtaining structure design with optimum performance of interest. However, the process requires numerical evaluation of objective function and constraints at each iteration, which…

Machine Learning · Computer Science 2022-03-22 Ren Kai Tan , Chao Qian , Dan Xu , Wenjing Ye

We present a particle flow realization of Bayes' rule, where an ODE-based neural operator is used to transport particles from a prior to its posterior after a new observation. We prove that such an ODE operator exists. Its neural…

Machine Learning · Computer Science 2020-01-03 Xinshi Chen , Hanjun Dai , Le Song