English
Related papers

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

200 papers

In practical applications of iterative first-order optimization, the learning rate schedule remains notoriously difficult to understand and expensive to tune. We demonstrate the presence of these subtleties even in the innocuous case when…

Machine Learning · Computer Science 2021-06-15 Naman Agarwal , Surbhi Goel , Cyril Zhang

Distributed optimization is pivotal for large-scale signal processing and machine learning, yet communication overhead remains a major bottleneck. Low-rank gradient compression, in which the transmitted gradients are approximated by…

Machine Learning · Computer Science 2025-10-21 Chuyan Chen , Yutong He , Pengrui Li , Weichen Jia , Kun Yuan

Scheduling precedence-constrained tasks under shared renewable resources is central to modern computing platforms. The Resource Investment Problem (RIP) models this setting by minimizing the cost of provisioned renewable resources under…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-09 Yi-Xiang Hu , Yuke Wang , Feng Wu , Zirui Huang , Shuli Zeng , Xiang-Yang Li

We study a logistic model-based active learning procedure for binary classification problems, in which we adopt a batch subject selection strategy with a modified sequential experimental design method. Moreover, accompanying the proposed…

Machine Learning · Statistics 2018-02-02 Hsiang-Ling Hsu , Yuan-Chin Ivan Chang , Ray-Bing Chen

We propose a theoretical framework for an adaptive learning rate policy for the Mean Absolute Error loss function and Quantile loss function and evaluate its effectiveness for regression tasks. The framework is based on the theory of…

Machine Learning · Computer Science 2020-06-25 Snehanshu Saha , Tejas Prashanth , Suraj Aralihalli , Sumedh Basarkod , T. S. B Sudarshan , Soma S Dhavala

We scale perceived distances of the core-set algorithm by a factor of uncertainty and search for low-confidence configurations, finding significant improvements in sample efficiency across CIFAR10/100 and SVHN image classification,…

Machine Learning · Computer Science 2022-02-10 Yuchen Li , Frank Rudzicz

Motion planning is an essential component in most of today's robotic applications. In this work, we consider the learning setting, where a set of solved motion planning problems is used to improve the efficiency of motion planning on…

Robotics · Computer Science 2019-06-04 Tom Jurgenson , Aviv Tamar

We consider the problem of approximating a given element $f$ from a Hilbert space $\mathcal{H}$ by means of greedy algorithms and the application of such procedures to the regression problem in statistical learning theory. We improve on the…

Statistics Theory · Mathematics 2009-09-29 Andrew R. Barron , Albert Cohen , Wolfgang Dahmen , Ronald A. DeVore

Random reshuffling, which randomly permutes the dataset each epoch, is widely adopted in model training because it yields faster convergence than with-replacement sampling. Recent studies indicate greedily chosen data orderings can further…

Machine Learning · Computer Science 2023-01-05 Yucheng Lu , Wentao Guo , Christopher De Sa

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…

Machine Learning · Computer Science 2020-10-01 Lang Huang , Chao Zhang , Hongyang Zhang

Regression problems are pervasive in real-world applications. Generally a substantial amount of labeled samples are needed to build a regression model with good generalization ability. However, many times it is relatively easy to collect a…

Machine Learning · Computer Science 2018-08-14 Dongrui Wu , Chin-Teng Lin , Jian Huang

Graph contrastive learning (GCL) has become a central paradigm for self-supervised representation learning in computational intelligence, with applications spanning recommendation, anomaly detection, and personalization. A key limitation of…

Machine Learning · Computer Science 2026-05-06 Adnan Ali , Jinlong Li , Syed Muhammad Israr , Ali Kashif Bashir

In most practical settings and theoretical analyses, one assumes that a model can be trained until convergence. However, the growing complexity of machine learning datasets and models may violate such assumptions. Indeed, current approaches…

Computer Vision and Pattern Recognition · Computer Science 2020-07-01 Mengtian Li , Ersin Yumer , Deva Ramanan

We introduce Dynamic Dropout, a novel regularization technique designed to enhance the training efficiency of Transformer models by dynamically adjusting the dropout rate based on training epochs or validation loss improvements. This…

Machine Learning · Computer Science 2024-11-06 Hanrui Yan , Dan Shao

To adapt to real-world data streams, continual learning (CL) systems must rapidly learn new concepts while preserving and utilizing prior knowledge. When it comes to adding new information to continually-trained deep neural networks (DNNs),…

Machine Learning · Computer Science 2025-07-02 Md Yousuf Harun , Christopher Kanan

Pollux improves scheduling performance in deep learning (DL) clusters by adaptively co-optimizing inter-dependent factors both at the per-job level and at the cluster-wide level. Most existing schedulers expect users to specify the number…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-05-27 Aurick Qiao , Sang Keun Choe , Suhas Jayaram Subramanya , Willie Neiswanger , Qirong Ho , Hao Zhang , Gregory R. Ganger , Eric P. Xing

In scalable machine learning systems, model training is often parallelized over multiple nodes that run without tight synchronization. Most analysis results for the related asynchronous algorithms use an upper bound on the information…

Machine Learning · Computer Science 2022-04-12 Xuyang Wu , Sindri Magnusson , Hamid Reza Feyzmahdavian , Mikael Johansson

The learning rate (LR) schedule is one of the most important hyper-parameters needing careful tuning in training DNNs. However, it is also one of the least automated parts of machine learning systems and usually costs significant manual…

Machine Learning · Computer Science 2021-05-25 Yuchen Jin , Tianyi Zhou , Liangyu Zhao , Yibo Zhu , Chuanxiong Guo , Marco Canini , Arvind Krishnamurthy

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to…

Machine Learning · Computer Science 2019-05-16 Chen Huang , Shuangfei Zhai , Walter Talbott , Miguel Angel Bautista , Shih-Yu Sun , Carlos Guestrin , Josh Susskind

We study optimal learning-rate schedules (LRSs) under the functional scaling law (FSL) framework introduced in Li et al. (2025), which accurately models the loss dynamics of both linear regression and large language model (LLM)…

Machine Learning · Statistics 2026-02-17 Binghui Li , Zilin Wang , Fengling Chen , Shiyang Zhao , Ruiheng Zheng , Lei Wu