English
Related papers

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

200 papers

Despite impressive performance, deep neural networks require significant memory and computation costs, prohibiting their application in resource-constrained scenarios. Sparse training is one of the most common techniques to reduce these…

Machine Learning · Computer Science 2023-12-06 Bowen Lei , Dongkuan Xu , Ruqi Zhang , Shuren He , Bani K. Mallick

At the heart of the standard deep learning training loop is a greedy gradient step minimizing a given loss. We propose to add a second step to maximize training generalization. To do this, we optimize the loss of the next training step.…

Machine Learning · Computer Science 2021-02-08 Samuel Müller , André Biedenkapp , Frank Hutter

In this paper, we investigate the use of deep learning for solving a classical NP-Hard single machine scheduling problem where the criterion is to minimize the total tardiness. Instead of designing an end-to-end machine learning model, we…

Artificial Intelligence · Computer Science 2020-05-13 Michal Bouška , Antonín Novák , Přemysl Šůcha , István Módos , Zdeněk Hanzálek

Training efficiency in large-scale models is typically assessed through memory consumption, training time, and model performance. Current methods often exhibit trade-offs among these metrics, as optimizing one generally degrades at least…

Machine Learning · Computer Science 2026-02-03 Tianhao Miao , Zhongyuan Bao , Lejun Zhang

The learning rate is a crucial hyperparameter in deep learning, with its ideal value depending on the problem and potentially changing during training. In this paper, we investigate the practical utility of adaptive learning rate mechanisms…

Machine Learning · Computer Science 2025-08-08 Asma Atamna , Tom Maus , Fabian Kievelitz , Tobias Glasmachers

We consider the problem of learning a loss function which, when minimized over a training dataset, yields a model that approximately minimizes a validation error metric. Though learning an optimal loss function is NP-hard, we present an…

Machine Learning · Computer Science 2019-07-02 Matthew Streeter

We hypothesize that due to the greedy nature of learning in multi-modal deep neural networks, these models tend to rely on just one modality while under-fitting the other modalities. Such behavior is counter-intuitive and hurts the models'…

Machine Learning · Computer Science 2022-09-20 Nan Wu , Stanisław Jastrzębski , Kyunghyun Cho , Krzysztof J. Geras

Modern machine learning is trained by stochastic gradient descent (SGD), whose performance critically depends on how the learning rate (LR) is adjusted and decreased over time. Yet existing LR regimes may be intricate, or need to tune one…

Machine Learning · Computer Science 2025-08-20 Zhuang Yang

The learning rate in stochastic gradient methods is a critical hyperparameter that is notoriously costly to tune via standard grid search, especially for training modern large-scale models with billions of parameters. We identify a…

Machine Learning · Computer Science 2026-02-17 Amit Attia , Tomer Koren

Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While for SGD, doubling the batch size can be equivalent to halving the learning rate, the optimal…

Machine Learning · Computer Science 2025-10-17 Alexandru Meterez , Depen Morwani , Jingfeng Wu , Costin-Andrei Oncescu , Cengiz Pehlevan , Sham Kakade

We propose EAGLE update rule, a novel optimization method that accelerates loss convergence during the early stages of training by leveraging both current and previous step parameter and gradient values. The update algorithm estimates…

Machine Learning · Computer Science 2025-02-04 Takumi Fujimoto , Hiroaki Nishi

Learning rate scheduling has evolved from the single global fixed rate of early SGD to sophisticated layer-wise adaptive strategies. We systematize this evolution into five generations: (Gen1) global fixed learning rates, (Gen2) global…

Artificial Intelligence · Computer Science 2026-05-01 Ming-Hong Yao , Di Wang , Jian Cui , Jin-Yan Chen , Zi-Hao Cui , Fa Wang , Chen Wei , Qiu-Ye Yu

In the usual deep neural network optimization process, the learning rate is the most important hyper parameter, which greatly affects the final convergence effect. The purpose of learning rate is to control the stepsize and gradually reduce…

Machine Learning · Computer Science 2019-05-02 Jiakai Wei

Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training. Learning rate schedules are widely used in real practice to adjust the learning rate according to pre-defined schedules…

Machine Learning · Computer Science 2022-08-26 Hengyu Liu , Qiang Fu , Lun Du , Tiancheng Zhang , Ge Yu , Shi Han , Dongmei Zhang

Loss of trainability refers to a phenomenon in continual learning where parameter updates no longer make progress on the optimization objective, so accuracy stalls or degrades as the learning problem changes over time. In this paper, we…

Machine Learning · Computer Science 2025-12-11 Gunbir Singh Baveja , Alex Lewandowski , Mark Schmidt

We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is…

Machine Learning · Computer Science 2023-12-29 Daphna Weinshall , Gad Cohen , Dan Amir

We investigate the task of learning to follow natural language instructions by jointly reasoning with visual observations and language inputs. In contrast to existing methods which start with learning from demonstrations (LfD) and then use…

Computation and Language · Computer Science 2018-07-10 Wenhan Xiong , Xiaoxiao Guo , Mo Yu , Shiyu Chang , Bowen Zhou , William Yang Wang

Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs' reasoning abilities, yet its data inefficiency remains a major bottleneck. To address this critical yet challenging issue, we present a…

Machine Learning · Computer Science 2026-04-28 Shipeng Li , Zhiqin Yang , Shikun Li , Xiaobo Xia , Hengyu Liu , Xinghua Zhang , Gaode Chen , Dong Fang , Ying Tai , Zhe Peng

We present and study a new model for energy-aware and profit-oriented scheduling on a single processor. The processor features dynamic speed scaling as well as suspension to a sleep mode. Jobs arrive over time, are preemptable, and have…

Data Structures and Algorithms · Computer Science 2012-09-14 Peter Kling , Andreas Cord-Landwehr , Frederik Mallmann-Trenn

It is well known that selecting samples with large losses/gradients can significantly reduce the number of training steps. However, the selection overhead is often too high to yield any meaningful gains in terms of overall training time. In…

Machine Learning · Computer Science 2025-06-05 Rudrajit Das , Xi Chen , Bertram Ieong , Parikshit Bansal , Sujay Sanghavi