English
Related papers

Related papers: Feed-Forward On-Edge Fine-tuning Using Static Synt…

200 papers

With the rapid increase of big data, distributed Machine Learning (ML) has been widely applied in training large-scale models. Stochastic Gradient Descent (SGD) is arguably the workhorse algorithm of ML. Distributed ML models trained by SGD…

Machine Learning · Computer Science 2021-12-09 Keyu Yang , Lu Chen , Zhihao Zeng , Yunjun Gao

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model…

Machine Learning · Computer Science 2026-05-01 Nghia Bui , Lijing Wang

Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key strategy for adapting large-scale pre-trained models to downstream tasks, but existing approaches face notable limitations. Addition-based methods, such as Adapters, introduce…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Kenneth Yang , Wen-Li Wei , Jen-Chun Lin

In this paper, we propose a generalized framework for developing learning-rate-free momentum stochastic gradient descent (SGD) methods in the minimization of nonsmooth nonconvex functions, especially in training nonsmooth neural networks.…

Optimization and Control · Mathematics 2024-06-27 Xiaoyin Hu , Nachuan Xiao , Xin Liu , Kim-Chuan Toh

Despite its importance for federated learning, continuous learning and many other applications, on-device training remains an open problem for EdgeAI. The problem stems from the large number of operations (e.g., floating point…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Yuedong Yang , Guihong Li , Radu Marculescu

The objective of this work is to explore how to effectively and efficiently adapt pre-trained visual foundation models to various downstream tasks of semantic segmentation. Previous methods usually fine-tuned the entire networks for each…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Lingbo Liu , Jianlong Chang , Bruce X. B. Yu , Liang Lin , Qi Tian , Chang-Wen Chen

Soft object manipulation tasks in domestic scenes pose a significant challenge for existing robotic skill learning techniques due to their complex dynamics and variable shape characteristics. Since learning new manipulation skills from…

Robotics · Computer Science 2023-09-06 Junjia Liu , Zhihao Li , Wanyu Lin , Sylvain Calinon , Kay Chen Tan , Fei Chen

Deep neural networks employing error back-propagation for learning can suffer from exploding and vanishing gradient problems. Numerous solutions have been proposed such as normalisation techniques or limiting activation functions to linear…

Machine Learning · Computer Science 2023-09-08 Sama Daryanavard , Bernd Porr

Gradient Boosting Machine has proven to be one successful function approximator and has been widely used in a variety of areas. However, since the training procedure of each base learner has to take the sequential order, it is infeasible to…

Machine Learning · Computer Science 2020-06-09 Ji Feng , Yi-Xuan Xu , Yuan Jiang , Zhi-Hua Zhou

Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate. The sensitivity to the learning rate is due to the reliance on backpropagation to train the network. In this paper we…

Machine Learning · Statistics 2018-08-08 Francois Fagan , Garud Iyengar

Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this challenge by updating only a subset of parameters. However, these approaches often limit…

Computation and Language · Computer Science 2026-04-10 Kaiyuan Tian , Yu Tang , Gongqingjian Jiang , Baihui Liu , Yifu Gao , Xialin Su , Linbo Qiao , Dongsheng Li

The backpropagation networks are notably susceptible to catastrophic forgetting, where networks tend to forget previously learned skills upon learning new ones. To address such the 'sensitivity-stability' dilemma, most previous efforts have…

Machine Learning · Computer Science 2021-10-12 Danruo Deng , Guangyong Chen , Jianye Hao , Qiong Wang , Pheng-Ann Heng

This paper introduces Selective-Backprop, a technique that accelerates the training of deep neural networks (DNNs) by prioritizing examples with high loss at each iteration. Selective-Backprop uses the output of a training example's forward…

We show that memory-augmented Transformers can implement the entire class of linear first-order methods (LFOMs), a class that contains gradient descent (GD) and more advanced methods such as conjugate gradient descent (CGD), momentum…

Machine Learning · Computer Science 2025-02-04 Sanchayan Dutta , Suvrit Sra

The data consistency for the physical forward model is crucial in inverse problems, especially in MR imaging reconstruction. The standard way is to unroll an iterative algorithm into a neural network with a forward model embedded. The…

Image and Video Processing · Electrical Eng. & Systems 2023-06-28 Guanxiong Luo , Mengmeng Kuang , Peng Cao

Oversmoothing has long been identified as a major limitation of Graph Neural Networks (GNNs): input node features are smoothed at each layer and converge to a non-informative representation, if the weights of the GNN are sufficiently…

Machine Learning · Computer Science 2026-03-16 Nicolas Keriven

Transfer learning is often used to decrease the computational cost of model training, as fine-tuning a model allows a downstream task to leverage the features learned from the pre-training dataset and quickly adapt them to a new task. This…

Machine Learning · Computer Science 2025-07-01 Joshua C. Zhao , Saurabh Bagchi

With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Emanuele Frascaroli , Aniello Panariello , Pietro Buzzega , Lorenzo Bonicelli , Angelo Porrello , Simone Calderara

Recent data-privacy laws have sparked interest in machine unlearning, which involves removing the effect of specific training samples from a learnt model as if they were never present in the original training dataset. The challenge of…

Machine Learning · Computer Science 2023-12-08 Tuan Hoang , Santu Rana , Sunil Gupta , Svetha Venkatesh

We study the problem of learning similarity functions over very large corpora using neural network embedding models. These models are typically trained using SGD with sampling of random observed and unobserved pairs, with a number of…

Machine Learning · Statistics 2018-07-20 Walid Krichene , Nicolas Mayoraz , Steffen Rendle , Li Zhang , Xinyang Yi , Lichan Hong , Ed Chi , John Anderson