English
Related papers

Related papers: Dynamic Learning Rate Scheduling based on Loss Cha…

200 papers

Code Large Language Models (CodeLLMs) are increasingly integrated into modern software development workflows, yet efficiently serving them in resource-constrained, self-hosted environments remains a significant challenge. Existing LLM…

Software Engineering · Computer Science 2025-06-26 Shi Chang , Boyuan Chen , Kishanthan Thangarajah , Hanan Lutfiyya , Ahmed E. Hassan

The success of modern deep learning is attributed to two key elements: huge amounts of training data and large model sizes. Where a vast amount of data allows the model to learn more features, the large model architecture boosts the…

Machine Learning · Computer Science 2024-10-08 Muhammad Asif Khan , Ridha Hamila , Hamid Menouar

Because loops execute their body many times, compiler developers place much emphasis on their optimization. Nevertheless, in view of highly diverse source code and hardware, compilers still struggle to produce optimal target code. The sheer…

Programming Languages · Computer Science 2021-03-01 Rahim Mammadli , Marija Selakovic , Felix Wolf , Michael Pradel

Deep neural networks (DNN) have achieved remarkable success in various fields, including computer vision and natural language processing. However, training an effective DNN model still poses challenges. This paper aims to propose a method…

Machine Learning · Computer Science 2024-07-03 Hejie Ying , Mengmeng Song , Yaohong Tang , Shungen Xiao , Zimin Xiao

A commonly cited inefficiency of neural network training using back-propagation is the update locking problem: each layer must wait for the signal to propagate through the full network before updating. Several alternatives that can…

Machine Learning · Computer Science 2021-06-14 Eugene Belilovsky , Louis Leconte , Lucas Caccia , Michael Eickenberg , Edouard Oyallon

Recent research has shown the existence of significant redundancy in large Transformer models. One can prune the redundant parameters without significantly sacrificing the generalization performance. However, we question whether the…

Computation and Language · Computer Science 2022-02-15 Chen Liang , Haoming Jiang , Simiao Zuo , Pengcheng He , Xiaodong Liu , Jianfeng Gao , Weizhu Chen , Tuo Zhao

Fine-tuning large language models on new data improves task performance but degrades capabilities learned during pretraining, a phenomenon known as catastrophic forgetting. Existing methods mitigate this by modifying the fine-tuning…

Machine Learning · Computer Science 2026-05-20 Parjanya Prajakta Prashant , Jiongli Zhu , Aldan Creo , Babak Salimi

With the rapid development of natural language processing technology, large-scale language models (LLM) have achieved remarkable results in a variety of tasks. However, how to effectively train these huge models and improve their…

Artificial Intelligence · Computer Science 2024-12-09 Jiajing Chen , Bingying Liu , Xiaoxuan Liao , Jia Gao , Hongye Zheng , Yue Li

Low precision training can significantly reduce the computational overhead of training deep neural networks (DNNs). Though many such techniques exist, cyclic precision training (CPT), which dynamically adjusts precision throughout training…

Machine Learning · Computer Science 2024-03-05 Cameron R. Wolfe , Anastasios Kyrillidis

Large scale machine learning and deep models are extremely data-hungry. Unfortunately, obtaining large amounts of labeled data is expensive, and training state-of-the-art models (with hyperparameter tuning) requires significant computing…

Machine Learning · Computer Science 2021-06-15 Krishnateja Killamsetty , Durga Sivasubramanian , Ganesh Ramakrishnan , Rishabh Iyer

Many machine learning models require a training procedure based on running stochastic gradient descent. A key element for the efficiency of those algorithms is the choice of the learning rate schedule. While finding good learning rates…

Machine Learning · Statistics 2020-06-26 Victor Picheny , Vincent Dutordoir , Artem Artemev , Nicolas Durrande

Recent progress on deep learning relies heavily on the quality and efficiency of training algorithms. In this paper, we develop a fast training method motivated by the nonlinear Conjugate Gradient (CG) framework. We propose the Conjugate…

Machine Learning · Computer Science 2021-07-28 Zhiyong Hao , Yixuan Jiang , Huihua Yu , Hsiao-Dong Chiang

Classically, ML models trained with stochastic gradient descent (SGD) are designed to minimize the average loss per example and use a distribution of training examples that remains {\em static} in the course of training. Research in recent…

Machine Learning · Computer Science 2020-06-02 Eliav Buchnik , Edith Cohen

Fueled by advances in distributed deep learning (DDL), recent years have witnessed a rapidly growing demand for resource-intensive distributed/parallel computing to process DDL computing jobs. To resolve network communication bottleneck and…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-02-03 Menglu Yu , Ye Tian , Bo Ji , Chuan Wu , Hridesh Rajan , Jia Liu

Federated learning has emerged in the last decade as a distributed optimization paradigm due to the rapidly increasing number of portable devices able to support the heavy computational needs related to the training of machine learning…

Machine Learning · Computer Science 2024-10-10 Emanuel Buttaci , Giuseppe Carlo Calafiore

Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward…

Machine Learning · Computer Science 2022-01-20 An Xu , Zhouyuan Huo , Heng Huang

When scaling distributed training, the communication overhead is often the bottleneck. In this paper, we propose a novel SGD variant with reduced communication and adaptive learning rates. We prove the convergence of the proposed algorithm…

Machine Learning · Computer Science 2020-12-08 Cong Xie , Oluwasanmi Koyejo , Indranil Gupta , Haibin Lin

We introduce a novel dynamic learning-rate scheduling scheme grounded in theory with the goal of simplifying the manual and time-consuming tuning of schedules in practice. Our approach is based on estimating the locally-optimal stepsize,…

Machine Learning · Computer Science 2023-11-27 Gilad Yehudai , Alon Cohen , Amit Daniely , Yoel Drori , Tomer Koren , Mariano Schain

In modern optimization methods used in deep learning, each update depends on the history of previous iterations, often referred to as memory, and this dependence decays fast as the iterates go further into the past. For example, gradient…

Machine Learning · Computer Science 2026-01-14 Matias D. Cattaneo , Boris Shigida

We propose a deep learning based method for simulating the large bending deformation of bilayer plates. Inspired by the greedy algorithm, we propose a pre-training method on a series of nested domains, which accelerate the convergence of…

Numerical Analysis · Mathematics 2024-07-16 Xiang Li , Yulei Liao , Pingbing Ming