English
Related papers

Related papers: GCSAM: Gradient Centralized Sharpness Aware Minimi…

200 papers

Normalization layers (e.g., Batch Normalization, Layer Normalization) were introduced to help with optimization difficulties in very deep nets, but they clearly also help generalization, even in not-so-deep nets. Motivated by the long-held…

Machine Learning · Computer Science 2023-01-18 Kaifeng Lyu , Zhiyuan Li , Sanjeev Arora

Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization…

Machine Learning · Computer Science 2018-09-19 Zijun Zhang , Lin Ma , Zongpeng Li , Chuan Wu

Deep multitask networks, in which one neural network produces multiple predictive outputs, can offer better speed and performance than their single-task counterparts but are challenging to train properly. We present a gradient normalization…

Computer Vision and Pattern Recognition · Computer Science 2018-07-16 Zhao Chen , Vijay Badrinarayanan , Chen-Yu Lee , Andrew Rabinovich

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is…

Machine Learning · Computer Science 2017-02-13 Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , Ping Tak Peter Tang

Normalization techniques are a boon for modern deep learning. They let weights converge more quickly with often better generalization performances. It has been argued that the normalization-induced scale invariance among the weights…

Machine Learning · Computer Science 2021-01-19 Byeongho Heo , Sanghyuk Chun , Seong Joon Oh , Dongyoon Han , Sangdoo Yun , Gyuwan Kim , Youngjung Uh , Jung-Woo Ha

In this work and its accompanying Part II [1], we develop an accelerated algorithmic framework, DAMA (Decentralized Accelerated Minimax Approach), for nonconvex Polyak-Lojasiewicz minimax optimization over decentralized multi-agent…

Optimization and Control · Mathematics 2025-12-17 Haoyuan Cai , Sulaiman A. Alghunaim , Ali H. Sayed

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed that compared with (stochastic) gradient descent, Adam can converge to a different solution with a…

Machine Learning · Computer Science 2021-08-26 Difan Zou , Yuan Cao , Yuanzhi Li , Quanquan Gu

Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environments. Sparse neural networks significantly alleviate these…

Machine Learning · Computer Science 2026-03-16 Jie Ji , Gen Li , Kaiyuan Deng , Fatemeh Afghah , Xiaolong Ma

Quantization has become a predominant approach for model compression, enabling deployment of large models trained on GPUs onto smaller form-factor devices for inference. Quantization-aware training (QAT) optimizes model parameters with…

Machine Learning · Computer Science 2022-12-13 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing…

Machine Learning · Computer Science 2025-10-09 Dung Hoang-Anh , Cuong Pham Trung Le , Jianfei Cai , Thanh-Toan Do

The main goal of network pruning is imposing sparsity on the neural network by increasing the number of parameters with zero value in order to reduce the architecture size and the computational speedup. In most of the previous research…

Computer Vision and Pattern Recognition · Computer Science 2019-01-17 Amirsina Torfi , Rouzbeh A. Shirvani , Sobhan Soleymani , Naser M. Nasrabadi

Real-world datasets exhibit imbalances of varying types and degrees. Several techniques based on re-weighting and margin adjustment of loss are often used to enhance the performance of neural networks, particularly on minority classes. In…

Machine Learning · Computer Science 2022-12-29 Harsh Rangwani , Sumukh K Aithal , Mayank Mishra , R. Venkatesh Babu

The stochastic gradient descent (SGD) method is most widely used for deep neural network (DNN) training. However, the method does not always converge to a flat minimum of the loss surface that can demonstrate high generalization capability.…

Machine Learning · Computer Science 2020-09-08 Wonyong Sung , Iksoo Choi , Jinhwan Park , Seokhyun Choi , Sungho Shin

Recently, foundation models have been introduced demonstrating various tasks in the field of computer vision. These models such as Segment Anything Model (SAM) are generalized models trained using huge datasets. Currently, ongoing research…

Computer Vision and Pattern Recognition · Computer Science 2023-06-23 Shurong Chai , Rahul Kumar Jain , Shiyu Teng , Jiaqing Liu , Yinhao Li , Tomoko Tateyama , Yen-wei Chen

Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to be sensitive to hyperparameter settings and make…

Machine Learning · Computer Science 2022-11-02 Masud An-Nur Islam Fahim , Jani Boutellier

The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning. While past studies confirm that the magnitude and the covariance structure of gradient noise are critical for…

Machine Learning · Computer Science 2020-06-22 Jingfeng Wu , Wenqing Hu , Haoyi Xiong , Jun Huan , Vladimir Braverman , Zhanxing Zhu

Deep learning models as an emerging topic have shown great progress in various fields. Especially, visualization tools such as class activation mapping methods provided visual explanation on the reasoning of convolutional neural networks…

Computer Vision and Pattern Recognition · Computer Science 2023-08-24 Ali Caglayan , Nevrez Imamoglu , Oguzhan Guclu , Ali Osman Serhatoglu , Weimin Wang , Ahmet Burak Can , Ryosuke Nakamura

Gaussian random matrix (GRM) has been widely used to generate linear measurements in compressed sensing (CS) of natural images. However, there actually exist two disadvantages with GRM in practice. One is that GRM has large memory…

Computer Vision and Pattern Recognition · Computer Science 2018-06-20 Wenxue Cui , Feng Jiang , Xinwei Gao , Wen Tao , Debin Zhao

The objective of domain generalization (DG) is to enhance the transferability of the model learned from a source domain to unobserved domains. To prevent overfitting to a specific domain, Sharpness-Aware Minimization (SAM) reduces source…

Machine Learning · Computer Science 2024-03-13 Seungjae Shin , HeeSun Bae , Byeonghu Na , Yoon-Yeong Kim , Il-Chul Moon

Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD). However, the estimation of the gradient using stochastic samples tends to be noisy and unreliable, resulting in large gradient variance and bad…

Machine Learning · Computer Science 2021-05-18 Xingyi Yang