English
Related papers

Related papers: How to Set the Batch Size for Large-Scale Pre-trai…

200 papers

There has been significant attention given to developing data-driven methods for tailoring patient care based on individual patient characteristics. Dynamic treatment regimes formalize this through a sequence of decision rules that map…

Methodology · Statistics 2022-02-22 Eric J. Rose , Erica E. M. Moodie , Susan Shortreed

As the size of deep learning models gets larger and larger, training takes longer time and more resources, making fault tolerance more and more critical. Existing state-of-the-art methods like CheckFreq and Elastic Horovod need to back up a…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-08-26 Yuchen Zhong , Guangming Sheng , Juncheng Liu , Jinhui Yuan , Chuan Wu

Recent advances in learning rate (LR) scheduling have demonstrated the effectiveness of decay-free approaches that eliminate the traditional decay phase while maintaining competitive performance. Model merging techniques have emerged as…

Computation and Language · Computer Science 2025-08-12 Changxin Tian , Jiapeng Wang , Qian Zhao , Kunlong Chen , Jia Liu , Ziqi Liu , Jiaxin Mao , Wayne Xin Zhao , Zhiqiang Zhang , Jun Zhou

In this work we consider the task of constructing prediction intervals in an inductive batch setting. We present a discriminative learning framework which optimizes the expected error rate under a budget constraint on the interval sizes.…

Machine Learning · Computer Science 2018-02-28 Nir Rosenfeld , Yishay Mansour , Elad Yom-Tov

Existing trajectory prediction methods exhibit significant performance degradation under distribution shifts during test time. Although test-time training techniques have been explored to enable adaptation, current approaches rely on an…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Yuning Wang , Pu Zhang , Yuan He , Ke Wang , Jianru Xue

Learning rate schedule has a major impact on the performance of deep learning models. Still, the choice of a schedule is often heuristical. We aim to develop a precise understanding of the effects of different learning rate schedules and…

Machine Learning · Computer Science 2020-02-25 Guillaume Leclerc , Aleksander Madry

Cloud data warehouses bill compute based on slot-time consumed. In shared multi-tenant environments, query cost is highly variable and hard to estimate before execution, causing budget overruns and degraded scheduling. Static query-planner…

Databases · Computer Science 2026-04-23 Prashant Kumar Pathak

Training language models currently requires pre-determining a fixed compute budget because the typical cosine learning rate schedule depends on the total number of steps. In contrast, the Warmup-Stable-Decay (WSD) schedule uses a constant…

Machine Learning · Computer Science 2024-12-04 Kaiyue Wen , Zhiyuan Li , Jason Wang , David Hall , Percy Liang , Tengyu Ma

The performance of deep neural network-based speech enhancement systems typically increases with the training dataset size. However, studies that investigated the effect of training dataset size on speech enhancement performance did not…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-10 Philippe Gonzalez , Zheng-Hua Tan , Jan Østergaard , Jesper Jensen , Tommy Sonne Alstrøm , Tobias May

Nowadays, the major challenge in machine learning is the Big Data challenge. The big data problems due to large number of data points or large number of features in each data point, or both, the training of models have become very slow. The…

Machine Learning · Computer Science 2018-07-26 Vinod Kumar Chauhan , Anuj Sharma , Kalpana Dahiya

Mini-batch optimization has proven to be a powerful paradigm for large-scale learning. However, the state of the art parallel mini-batch algorithms assume synchronous operation or cyclic update orders. When worker nodes are heterogeneous…

Optimization and Control · Mathematics 2015-05-20 Hamid Reza Feyzmahdavian , Arda Aytekin , Mikael Johansson

Conformal prediction (CP) is a promising uncertainty quantification framework which works as a wrapper around a black-box classifier to construct prediction sets (i.e., subset of candidate classes) with provable guarantees. However,…

Machine Learning · Computer Science 2025-06-10 Yuanjie Shi , Hooman Shahrokhi , Xuesong Jia , Xiongzhi Chen , Janardhan Rao Doppa , Yan Yan

Motivated by the increasing popularity of learning and predicting human user behavior in communication and computing systems, in this paper, we investigate the fundamental benefit of predictive scheduling, i.e., predicting and pre-serving…

Optimization and Control · Mathematics 2013-09-05 Longbo Huang , Shaoquan Zhang , Minghua Chen , Xin Liu

Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining representations without explicit labels. When it comes to…

Machine Learning · Computer Science 2023-01-25 Yanchao Sun , Shuang Ma , Ratnesh Madaan , Rogerio Bonatti , Furong Huang , Ashish Kapoor

The pursuit of long-term autonomy mandates that machine learning models must continuously adapt to their changing environments and learn to solve new tasks. Continual learning seeks to overcome the challenge of catastrophic forgetting,…

Machine Learning · Computer Science 2024-07-25 Jack Foster , Alexandra Brintrup

Estimation-of-distribution algorithms (EDAs) are optimization algorithms that learn a distribution on the search space from which good solutions can be sampled easily. A key parameter of most EDAs is the sample size (population size). If…

Neural and Evolutionary Computing · Computer Science 2023-11-06 Weijie Zheng , Benjamin Doerr

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution is to continually pre-train these models, saving significant…

We study the impact of the batch size $n_b$ on the iteration time $T$ of training two-layer neural networks with one-pass stochastic gradient descent (SGD) on multi-index target functions of isotropic covariates. We characterize the optimal…

Machine Learning · Statistics 2024-09-06 Luca Arnaboldi , Yatin Dandi , Florent Krzakala , Bruno Loureiro , Luca Pesce , Ludovic Stephan

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual…

In this paper, we revisit the large-scale constrained linear regression problem and propose faster methods based on some recent developments in sketching and optimization. Our algorithms combine (accelerated) mini-batch SGD with a new…

Machine Learning · Computer Science 2018-02-12 Di Wang , Jinhui Xu
‹ Prev 1 8 9 10 Next ›