English
Related papers

Related papers: Fast training of large kernel models with delayed …

200 papers

In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance. This issue is usually tackled by delay tolerant algorithms with some mild assumptions on the objective…

Machine Learning · Computer Science 2024-10-28 Haoxiang Wang , Zhanhong Jiang , Chao Liu , Soumik Sarkar , Dongxiang Jiang , Young M. Lee

Deep neural networks are capable of modelling highly non-linear functions by capturing different levels of abstraction of data hierarchically. While training deep networks, first the system is initialized near a good optimum by greedy…

Machine Learning · Computer Science 2016-03-10 Anirban Santara , Debapriya Maji , DP Tejas , Pabitra Mitra , Arobinda Gupta

Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration…

Machine Learning · Computer Science 2022-07-07 Ryuichi Ito , Seng Pei Liew , Tsubasa Takahashi , Yuya Sasaki , Makoto Onizuka

Traditional CNN models are trained and tested on relatively low resolution images (<300 px), and cannot be directly operated on large-scale images due to compute and memory constraints. We propose Patch Gradient Descent (PatchGD), an…

Computer Vision and Pattern Recognition · Computer Science 2023-02-01 Deepak K. Gupta , Gowreesh Mago , Arnav Chavan , Dilip K. Prasad

CNNs are increasingly deployed across different hardware, dynamic environments, and low-power embedded devices. This has led to the design and training of CNN architectures with the goal of maximizing accuracy subject to such variable…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Aditya Annavajjala , Alind Khare , Animesh Agrawal , Igor Fedorov , Hugo Latapie , Myungjin Lee , Alexey Tumanov

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Machine Learning · Computer Science 2020-06-11 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi

Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent. Second-order optimization methods, that involve second derivatives and/or second…

Machine Learning · Computer Science 2021-03-08 Rohan Anil , Vineet Gupta , Tomer Koren , Kevin Regan , Yoram Singer

Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gradients into a lower-dimensional subspace to reduce optimizer…

Machine Learning · Computer Science 2024-06-26 Aashiq Muhamed , Oscar Li , David Woodruff , Mona Diab , Virginia Smith

We consider a class of statistical inverse problems involving the estimation of a regression operator from a Polish space to a separable Hilbert space, where the target lies in a vector-valued reproducing kernel Hilbert space induced by an…

Machine Learning · Statistics 2026-04-28 Jia-Qi Yang , Lei Shi

A major challenge in training large-scale machine learning models is configuring the training process to maximize model performance, i.e., finding the best training setup from a vast design space. In this work, we unlock a gradient-based…

Machine Learning · Statistics 2025-03-19 Logan Engstrom , Andrew Ilyas , Benjamin Chen , Axel Feldmann , William Moses , Aleksander Madry

After the tremendous development of neural networks trained by backpropagation, it is a good time to develop other algorithms for training neural networks to gain more insights into networks. In this paper, we propose a new algorithm for…

Machine Learning · Computer Science 2020-07-01 Benyamin Ghojogh , Fakhri Karray , Mark Crowley

The burgeoning computational demands for training large language models (LLMs) necessitate efficient methods, including quantized training, which leverages low-bit arithmetic operations to reduce costs. While FP8 precision has shown…

Machine Learning · Computer Science 2025-02-18 Jiecheng Zhou , Ding Tang , Rong Fu , Boni Hu , Haoran Xu , Yi Wang , Zhilin Pei , Zhongling Su , Liang Liu , Xingcheng Zhang , Weiming Zhang

With the fast development of deep learning, it has become common to learn big neural networks using massive training data. Asynchronous Stochastic Gradient Descent (ASGD) is widely adopted to fulfill this task for its efficiency, which is,…

Machine Learning · Computer Science 2020-02-19 Shuxin Zheng , Qi Meng , Taifeng Wang , Wei Chen , Nenghai Yu , Zhi-Ming Ma , Tie-Yan Liu

Following AI scaling trends, frontier models continue to grow in size and continue to be trained on larger datasets. Training these models requires huge investments in exascale computational resources, which has in turn driven developtment…

Machine Learning · Computer Science 2025-09-18 Hiroki Naganuma , Xinzhi Zhang , Man-Chung Yue , Ioannis Mitliagkas , Philipp A. Witte , Russell J. Hewett , Yin Tat Lee

This paper presents a new method for pre-training neural networks that can decrease the total training time for a neural network while maintaining the final performance, which motivates its use on deep neural networks. By partitioning the…

Neural and Evolutionary Computing · Computer Science 2016-01-05 Conrado S. Miranda , Fernando J. Von Zuben

We design scalable neural networks adapted to translational symmetries in dynamical systems, capable of inferring untrained high-dimensional dynamics for different system sizes. We train these networks to predict the dynamics of…

Machine Learning · Computer Science 2024-07-08 Mirko Goldmann , Claudio R. Mirasso , Ingo Fischer , Miguel C. Soriano

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been…

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

We develop an approach to efficiently grow neural networks, within which parameterization and optimization strategies are designed by considering their effects on the training dynamics. Unlike existing growing methods, which follow simple…

Machine Learning · Computer Science 2023-06-23 Xin Yuan , Pedro Savarese , Michael Maire

Spiking neural networks (SNNs) represent a promising approach in machine learning, combining the hierarchical learning capabilities of deep neural networks with the energy efficiency of spike-based computations. Traditional end-to-end…

Neural and Evolutionary Computing · Computer Science 2024-11-12 Ruyin Wan , Qian Zhang , George Em Karniadakis