English
Related papers

Related papers: Mixed Precision Training of Neural ODEs

200 papers

Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in graph learning and scientific machine learning. We present…

Machine Learning · Computer Science 2024-12-17 Hong Zhang , Ying Liu , Romit Maulik

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

Although double-precision floating-point arithmetic currently dominates high-performance computing, there is increasing interest in smaller and simpler arithmetic types. The main reasons are potential improvements in energy efficiency and…

Data Structures and Algorithms · Computer Science 2020-01-23 Michael Hopkins , Mantas Mikaitis , Dave R. Lester , Steve Furber

Neural networks are universal approximators and are studied for their use in solving differential equations. However, a major criticism is the lack of error bounds for obtained solutions. This paper proposes a technique to rigorously…

Computational Engineering, Finance, and Science · Computer Science 2023-06-07 Shuheng Liu , Xiyue Huang , Pavlos Protopapas

This short, self-contained article seeks to introduce and survey continuous-time deep learning approaches that are based on neural ordinary differential equations (neural ODEs). It primarily targets readers familiar with ordinary and…

Machine Learning · Computer Science 2024-01-09 Lars Ruthotto

Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that…

Machine Learning · Computer Science 2018-12-04 Shiqi Wang , Yizheng Chen , Ahmed Abdou , Suman Jana

Mixed-precision algorithms combine low- and high-precision computations in order to benefit from the performance gains of reduced-precision without sacrificing accuracy. In this work, we design mixed-precision Runge-Kutta-Chebyshev (RKC)…

Numerical Analysis · Mathematics 2023-01-10 Matteo Croci , Giacomo Rosilho de Souza

Large Language and Vision Models using a Mixture-of-Experts (MoE) architecture pose significant challenges for deployment due to their computational and memory demands. Mixed Precision Quantization assigns different precisions to different…

Machine Learning · Computer Science 2025-09-03 Krishna Teja Chitty-Venkata , Jie Ye , Murali Emani

Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While this reduces computation, the large number of parameters still incurs substantial memory…

In this paper, we evaluate training of deep recurrent neural networks with half-precision floats. We implement a distributed, data-parallel, synchronous training algorithm by integrating TensorFlow and CUDA-aware MPI to enable execution…

Machine Learning · Computer Science 2019-12-03 Alexey Svyatkovskiy , Julian Kates-Harbeck , William Tang

Renewed interest in mixed-precision algorithms has emerged due to growing data capacity and bandwidth concerns, as well as the advancement of GPUs, which enable significant speedup for low precision arithmetic. In light of this, we propose…

Numerical Analysis · Mathematics 2020-12-14 Alec Michael Dunton , Alyson Fox

Neural ordinary differential equations (ODEs) have attracted much attention as continuous-time counterparts of deep residual neural networks (NNs), and numerous extensions for recurrent NNs have been proposed. Since the 1980s, ODEs have…

Machine Learning · Computer Science 2022-10-17 Kazuki Irie , Francesco Faccio , Jürgen Schmidhuber

In the last decade, deep learning has become a major component of artificial intelligence. The workhorse of deep learning is the optimization of loss functions by stochastic gradient descent (SGD). Traditionally in deep learning, neural…

Machine Learning · Computer Science 2021-04-27 Benjamin Scellier

This paper presents a novel deep learning framework for solving multiple optimal stopping problems in high dimensions. While deep learning has recently shown promise for single stopping problems, the multiple exercise case involves complex…

Optimization and Control · Mathematics 2025-12-30 Mathieu Laurière , Mehdi Talbi

This paper presents the design, implementation, and evaluation of the PyTorch distributed data parallel module. PyTorch is a widely-adopted scientific computing package used in deep learning research and applications. Recent advances in…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-30 Shen Li , Yanli Zhao , Rohan Varma , Omkar Salpekar , Pieter Noordhuis , Teng Li , Adam Paszke , Jeff Smith , Brian Vaughan , Pritam Damania , Soumith Chintala

Large-scale deep learning models contribute to significant performance improvements on varieties of downstream tasks. Current data and model parallelism approaches utilize model replication and partition techniques to support the…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-19 Youhe Jiang , Fangcheng Fu , Xupeng Miao , Xiaonan Nie , Bin Cui

We improve the accuracy of Guidance & Control Networks (G&CNETs), trained to represent the optimal control policies of a time-optimal transfer and a mass-optimal landing, respectively. In both cases we leverage the dynamics of the…

Machine Learning · Computer Science 2024-04-29 Sebastien Origer , Dario Izzo

Neural networks are discrete entities: subdivided into discrete layers and parametrized by weights which are iteratively optimized via difference equations. Recent work proposes networks with layer outputs which are no longer quantized but…

Neural and Evolutionary Computing · Computer Science 2019-09-09 Stefano Massaroli , Michael Poli , Federico Califano , Angela Faragasso , Jinkyoo Park , Atsushi Yamashita , Hajime Asama

This paper introduces Laplace techniques for designing a neural network, with the goal of estimating simplex-constraint sparse vectors from compressed measurements. To this end, we recast the problem of MMSE estimation (w.r.t. a pre-defined…

Information Theory · Computer Science 2017-09-28 Steffen Limmer , Slawomir Stanczak

Large-scale deep learning models contribute to significant performance improvements on varieties of downstream tasks. Current data and model parallelism approaches utilize model replication and partition techniques to support the…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-22 Youhe Jiang , Fangcheng Fu , Xupeng Miao , Xiaonan Nie , Bin Cui