English
Related papers

Related papers: kDecay: Just adding k-decay items on Learning-Rate…

200 papers

Learning rate scheduler has been a critical issue in the deep neural network training. Several schedulers and methods have been proposed, including step decay scheduler, adaptive method, cosine scheduler and cyclical scheduler. This paper…

Computer Vision and Pattern Recognition · Computer Science 2018-11-14 Bo Yang Hsueh , Wei Li , I-Chen Wu

Despite significant advances in optimizers for training, most research works use common scheduler choices like Cosine or exponential decay. In this paper, we study \emph{GreedyLR}, a novel scheduler that adaptively adjusts the learning rate…

Artificial Intelligence · Computer Science 2025-12-17 Shreyas Subramanian , Bala Krishnamoorthy , Pranav Murthy

It is known that the learning rate is the most important hyper-parameter to tune for training deep neural networks. This paper describes a new method for setting the learning rate, named cyclical learning rates, which practically eliminates…

Computer Vision and Pattern Recognition · Computer Science 2017-04-05 Leslie N. Smith

In this work, we introduce a novel approach for optimizing LLM training by adjusting learning rates across weights of different components in Transformer models. Traditional methods often apply a uniform learning rate across all network…

The importance of learning rate (LR) schedules on network pruning has been observed in a few recent works. As an example, Frankle and Carbin (2019) highlighted that winning tickets (i.e., accuracy preserving subnetworks) can not be found…

Machine Learning · Computer Science 2023-01-03 Shiyu Liu , Rohan Ghosh , John Tan Chong Min , Mehul Motani

Complex learning rate schedules have become an integral part of deep learning. We find empirically that common fine-tuned schedules decay the learning rate after the weight norm bounces. This leads to the proposal of ABEL: an automatic…

Machine Learning · Computer Science 2021-03-24 Aitor Lewkowycz

Learning rate schedulers have shown great success in speeding up the convergence of learning algorithms in practice. However, their convergence to a minimum has not been proven theoretically. This difficulty mainly arises from the fact…

Machine Learning · Computer Science 2025-05-21 Dahlia Devapriya , Thulasi Tholeti , Janani Suresh , Sheetal Kalyani

The learning rate schedule is one of the most impactful aspects of neural network optimization, yet most schedules either follow simple parametric functions or react only to short-term training signals. None of them are supported by a…

Machine Learning · Computer Science 2025-09-30 Matt L. Sampson , Peter Melchior

Large-batch training has been essential in leveraging large-scale datasets and models in deep learning. While it is computationally beneficial to use large batch sizes, it often requires a specially designed learning rate (LR) schedule to…

Machine Learning · Computer Science 2021-07-14 Chiheon Kim , Saehoon Kim , Jongmin Kim , Donghoon Lee , Sungwoong Kim

Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs). Even for the baseline of a constant learning rate, it is non-trivial to choose a good constant value for training a DNN.…

Machine Learning · Computer Science 2019-10-29 Yanzhao Wu , Ling Liu , Juhyun Bae , Ka-Ho Chow , Arun Iyengar , Calton Pu , Wenqi Wei , Lei Yu , Qi Zhang

In this paper, we propose a principled deep reinforcement learning (RL) approach that is able to accelerate the convergence rate of general deep neural networks (DNNs). With our approach, a deep RL agent (synonym for optimizer in this work)…

Machine Learning · Computer Science 2017-07-14 Jie Fu

We explore a new perspective on adapting the learning rate (LR) schedule to improve the performance of the ReLU-based network as it is iteratively pruned. Our work and contribution consist of four parts: (i) We find that, as the ReLU-based…

Machine Learning · Computer Science 2021-10-19 Shiyu Liu , Chong Min John Tan , Mehul Motani

Intriguing empirical evidence exists that deep learning can work well with exoticschedules for varying the learning rate. This paper suggests that the phenomenon may be due to Batch Normalization or BN, which is ubiquitous and provides…

Machine Learning · Computer Science 2019-11-22 Zhiyuan Li , Sanjeev Arora

Training neural networks can be challenging, especially as the complexity of the problem increases. Despite using wider or deeper networks, training them can be a tedious process, especially if a wrong choice of the hyperparameter is made.…

Computational Engineering, Finance, and Science · Computer Science 2025-07-30 D. Veerababu , Ashwin A. Raikar , Prasanta K. Ghosh

Effective learning rate (LR) scheduling is crucial for training deep neural networks. However, popular pre-defined and adaptive schedulers can still lead to suboptimal generalization. This paper introduces VolSched, a novel adaptive LR…

Machine Learning · Computer Science 2025-07-16 Kieran Chai Kai Ren

Low Rank Decomposition (LRD) is a model compression technique applied to the weight tensors of deep learning models in order to reduce the number of trainable parameters and computational complexity. However, due to high number of new…

Machine Learning · Computer Science 2025-05-27 Habib Hajimolahoseini , Walid Ahmed , Yang Liu

In this paper, we study the problem of improving computational resource utilization of neural networks. Deep neural networks are usually over-parameterized for their tasks in order to achieve good performances, thus are likely to have…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Siyuan Qiao , Zhe Lin , Jianming Zhang , Alan Yuille

Most curriculum learning methods require an approach to sort the data samples by difficulty, which is often cumbersome to perform. In this work, we propose a novel curriculum learning approach termed Learning Rate Curriculum (LeRaC), which…

Machine Learning · Computer Science 2024-07-23 Florinel-Alin Croitoru , Nicolae-Catalin Ristea , Radu Tudor Ionescu , Nicu Sebe

We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. In this setup, the worst-case expected loss after $k$ learning iterations admits a lower bound of…

Machine Learning · Computer Science 2025-10-28 Ran Levinstein , Amit Attia , Matan Schliserman , Uri Sherman , Tomer Koren , Daniel Soudry , Itay Evron

Deep learning has excelled in image recognition tasks through neural networks inspired by the human brain. However, the necessity for large models to improve prediction accuracy introduces significant computational demands and extended…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Taigo Sakai , Kazuhiro Hotta