English
Related papers

Related papers: Pay Attention to Small Weights

200 papers

Training neural networks requires significant computational resources and energy. Methods like mixed-precision and quantization-aware training reduce bit usage, yet they still depend heavily on computationally expensive gradient-based…

Machine Learning · Computer Science 2025-09-30 Noa Cohen , Omkar Joglekar , Dotan Di Castro , Vladimir Tchuiev , Shir Kozlovsky , Michal Moshkovitz

Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to…

Machine Learning · Computer Science 2025-12-09 Yehonathan Refael , Jonathan Svirsky , Boris Shustin , Wasim Huleihel , Ofir Lindenbaum

Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures…

Machine Learning · Computer Science 2018-06-19 Utku Evci

Neural network potentials (NNPs) are crucial for accelerating computational materials science by surrogating density functional theory (DFT) calculations. Improving their accuracy is possible through pre-training and fine-tuning, where an…

Machine Learning · Computer Science 2025-05-29 Yosuke Oyama , Yusuke Majima , Eiji Ohta , Yasufumi Sakai

Fine-tuning large pre-trained foundation models often yields excellent downstream performance but is prohibitively expensive when updating all parameters. Parameter-efficient fine-tuning (PEFT) methods such as LoRA alleviate this by…

Machine Learning · Computer Science 2025-11-25 Yibo Zhong , Haoxiang Jiang , Lincan Li , Ryumei Nakada , Tianci Liu , Linjun Zhang , Huaxiu Yao , Haoyu Wang

Training large language models (LLMs) is often bottlenecked by extreme memory demands, with optimizer states dominating the footprint. Recent works mitigates this cost by projecting gradients into low-dimensional subspaces using…

Machine Learning · Computer Science 2025-10-03 Sahar Rajabi , Nayeema Nonta , Samanvay Vajpayee , Sirisha Rambhatla

We introduce LDAdam, a memory-efficient optimizer for training large models, that performs adaptive optimization steps within lower dimensional subspaces, while consistently exploring the full parameter space during training. This strategy…

Machine Learning · Computer Science 2025-03-04 Thomas Robert , Mher Safaryan , Ionut-Vlad Modoranu , Dan Alistarh

Several recent works [40, 24] observed an interesting phenomenon in neural network pruning: A larger finetuning learning rate can improve the final performance significantly. Unfortunately, the reason behind it remains elusive up to date.…

Machine Learning · Computer Science 2021-05-14 Huan Wang , Can Qin , Yue Bai , Yun Fu

In recent years, deep neural networks have known a wide success in various application domains. However, they require important computational and memory resources, which severely hinders their deployment, notably on mobile devices or for…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Nathan Hubens , Matei Mancas , Bernard Gosselin , Marius Preda , Titus Zaharia

What makes untrained deep neural networks (DNNs) different from the trained performant ones? By zooming into the weights in well-trained DNNs, we found it is the location of weights that hold most of the information encoded by the training.…

Machine Learning · Computer Science 2020-12-08 Yushi Qiu , Reiji Suda

We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of…

Machine Learning · Computer Science 2021-06-22 Benedict Leimkuhler , Tiffany Vlaar , Timothée Pouchon , Amos Storkey

Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple loss terms act as hyperparameters. Tuning these weights with random search or Bayesian…

Machine Learning · Computer Science 2026-05-11 Ivan Karpukhin , Andrey Savchenko

The recently proposed optimization algorithm for deep neural networks Sharpness Aware Minimization (SAM) suggests perturbing parameters before gradient calculation by a gradient ascent step to guide the optimization into parameter space…

Machine Learning · Computer Science 2025-10-03 Marlon Becker , Frederick Altrock , Benjamin Risse

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural…

Machine Learning · Computer Science 2016-11-08 Ark Anderson , Kyle Shaffer , Artem Yankov , Court D. Corley , Nathan O. Hodas

Large Language Models (LLMs) are typically trained in two phases: pre-training on large internet-scale datasets, and fine-tuning for downstream tasks. Given the higher computational demand of pre-training, it's intuitive to assume that…

Machine Learning · Computer Science 2024-10-15 James Liu , Guangxuan Xiao , Kai Li , Jason D. Lee , Song Han , Tri Dao , Tianle Cai

Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD):…

Machine Learning · Statistics 2018-01-09 Haw-Shiuan Chang , Erik Learned-Miller , Andrew McCallum

Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the…

Deep neural networks have enabled progress in a wide variety of applications. Growing the size of the neural network typically results in improved accuracy. As model sizes grow, the memory and compute requirements for training these models…

This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…

Machine Learning · Computer Science 2020-05-26 Mohammed Sharafath Abdul Hameed , Gavneet Singh Chadha , Andreas Schwung , Steven X. Ding

Weight decay is a simple yet powerful regularization technique that has been very widely used in training of deep neural networks (DNNs). While weight decay has attracted much attention, previous studies fail to discover some overlooked…

Machine Learning · Computer Science 2024-08-19 Zeke Xie , Zhiqiang Xu , Jingzhao Zhang , Issei Sato , Masashi Sugiyama
‹ Prev 1 2 3 10 Next ›