English
Related papers

Related papers: Memory Efficient Mixed-Precision Optimizers

200 papers

In this paper we consider bound-constrained mixed-integer optimization problems where the objective function is differentiable w.r.t.\ the continuous variables for every configuration of the integer variables. We mainly suggest to exploit…

Optimization and Control · Mathematics 2026-01-19 Matteo Lapucci , Giampaolo Liuzzi , Stefano Lucidi , Pierluigi Mansueto

Iterative differential approximation methods that rely upon backpropagation have enabled the optimization of neural networks; however, at present, they remain computationally expensive, especially when training models at scale. In this…

Machine Learning · Computer Science 2023-11-14 Jake Ryland Williams , Haoran Zhao

Gradient-based bilevel optimisation is a powerful technique with applications in hyperparameter optimisation, task adaptation, algorithm discovery, meta-learning more broadly, and beyond. It often requires differentiating through the…

Machine Learning · Computer Science 2025-06-11 Iurii Kemaev , Dan A Calian , Luisa M Zintgraf , Gregory Farquhar , Hado van Hasselt

We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of…

Neural and Evolutionary Computing · Computer Science 2016-06-13 Audrūnas Gruslys , Remi Munos , Ivo Danihelka , Marc Lanctot , Alex Graves

Ootomo, Ozaki, and Yokota [Int. J. High Perform. Comput. Appl., 38 (2024), p. 297-313] have proposed a strategy to recast a floating-point matrix multiplication in terms of integer matrix products. The factors A and B are split into integer…

Numerical Analysis · Mathematics 2026-05-11 Ahmad Abdelfattah , Jack Dongarra , Massimiliano Fasi , Mantas Mikaitis , Françoise Tisseur

Large neural networks spend most computation on floating point tensor multiplications. In this work, we find that a floating point multiplier can be approximated by one integer adder with high precision. We propose the linear-complexity…

Computation and Language · Computer Science 2024-10-03 Hongyin Luo , Wei Sun

The study addresses the problem of precision in floating-point (FP) computations. A method for estimating the errors which affect intermediate and final results is proposed and a summary of many software simulations is discussed. The basic…

Numerical Analysis · Computer Science 2012-01-31 Glauco Masotti

This article studies a combination of the two state-of-the-art algorithms for the exact solution of linear programs (LPs) over the rational numbers, i.e., without any roundoff errors or numerical tolerances. By integrating the method of…

Optimization and Control · Mathematics 2023-11-15 Leon Eifler , Jules Nicolas-Thouvenin , Ambros Gleixner

This work explores an extension of machine learning-optimized piecewise polynomial approximation by incorporating energy optimization as an additional objective. Traditional closed-form solutions enable continuity and approximation targets…

Machine Learning · Computer Science 2025-08-08 Hannes Waclawek , Stefan Huber

We present a scheme to automatically set the precision of floating point variables in an application. We design a framework that profiles applications to measure undesirable numerical behavior at the floating point operation level. We use…

Numerical Analysis · Computer Science 2016-06-02 Ralph Nathan , Helia Naeimi , Daniel J. Sorin , Xiaobai Sun

Mixed-precision Deep Neural Networks achieve the energy efficiency and throughput needed for hardware deployment, particularly when the resources are limited, without sacrificing accuracy. However, the optimal per-layer bit precision that…

Machine Learning · Computer Science 2022-08-15 Mariam Rakka , Mohammed E. Fouda , Pramod Khargonekar , Fadi Kurdahi

Block Floating Point (BFP) arithmetic is currently seeing a resurgence in interest because it requires less power, less chip area, and is less complicated to implement in hardware than standard floating point arithmetic. This paper explores…

Numerical Analysis · Mathematics 2023-07-04 Nils Kohl , Stephen F. McCormick , Rasmus Tamstorf

Thanks to the computational power of modern cluster machines, numerical simulations can provide, with an unprecedented level of details, new insights into fluid mechanics. However, taking full advantage of this hardware remains challenging…

Fluid Dynamics · Physics 2022-09-14 F. Brogi , S. Bnà , G. Boga , G. Amati , T. Esposti Ongaro , M. Cerminara

Low-precision formats have proven to be an efficient way to reduce not only the memory footprint but also the hardware resources and power consumption of deep learning computations. Under this premise, the posit numerical format appears to…

Machine Learning · Computer Science 2021-05-17 Gonçalo Raposo , Pedro Tomás , Nuno Roma

Memory footprint is one of the main limiting factors for large neural network training. In backpropagation, one needs to store the input to each operation in the computational graph. Every modern neural network model has quite a few…

Machine Learning · Computer Science 2022-02-04 Georgii Novikov , Daniel Bershatsky , Julia Gusak , Alex Shonenkov , Denis Dimitrov , Ivan Oseledets

Exploiting low-precision computations has become a standard strategy in deep learning to address the growing computational costs imposed by ever larger models and datasets. However, naively performing all computations in low precision can…

Machine Learning · Computer Science 2026-05-01 Elena Celledoni , Brynjulf Owren , Lars Ruthotto , Tianjiao Nicole Yang

Deep neural networks are increasingly bottlenecked by the cost of optimization, both in terms of GPU memory and compute time. Existing acceleration techniques, such as mixed precision, second-order methods, and batch size scaling, are…

Machine Learning · Computer Science 2025-09-03 Mohsen Sheibanian , Pouya Shaeri , Alimohammad Beigi , Ryan T. Woo , Aryan Keluskar

The super point, a host which communicates with lots of others, is a kind of special hosts gotten great focus. Mining super point at the edge of a network is the foundation of many network research fields. In this paper, we proposed the…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-01-29 Jie Xu , Wei Ding , Xiaoyan Hu

Minimizing loss functions is central to machine-learning training. Although first-order methods dominate practical applications, higher-order techniques such as Newton's method can deliver greater accuracy and faster convergence, yet are…

Machine Learning · Computer Science 2025-11-25 Giuseppe Carrino , Elena Loli Piccolomini , Elisa Riccietti , Theo Mary

The limited memory steepest descent method (Fletcher, 2012) for unconstrained optimization problems stores a few past gradients to compute multiple stepsizes at once. We review this method and propose new variants. For strictly convex…

Optimization and Control · Mathematics 2024-04-17 Giulia Ferrandi , Michiel E. Hochstenbach