English
Related papers

Related papers: Flatness and Gradient Alignment Are Both Necessary…

200 papers

The goal of multi-task learning is to enable more efficient learning than single task learning by sharing model structures for a diverse set of tasks. A standard multi-task learning objective is to minimize the average loss across all…

Machine Learning · Computer Science 2024-02-22 Bo Liu , Xingchao Liu , Xiaojie Jin , Peter Stone , Qiang Liu

Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced. As these applications make high-stake decisions…

Machine Learning · Computer Science 2021-09-16 Chao Chen , Yifan Shen , Guixiang Ma , Xiangnan Kong , Srinivas Rangarajan , Xi Zhang , Sihong Xie

Cloud computing is becoming increasingly popular as a platform for distributed training of deep neural networks. Synchronous stochastic gradient descent (SSGD) suffers from substantial slowdowns due to stragglers if the environment is…

Machine Learning · Computer Science 2020-02-04 Saar Barkai , Ido Hakimi , Assaf Schuster

Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Bingyuan Liu , Jérôme Rony , Adrian Galdran , Jose Dolz , Ismail Ben Ayed

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

Machine Learning · Computer Science 2026-05-19 Michał Brzozowski , Neo Christopher Chung

Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR) used by AGMs varies significantly across the dimensions of…

Machine Learning · Computer Science 2019-09-12 Qianqian Tong , Guannan Liang , Jinbo Bi

We analyze the training dynamics for deep linear networks using a new metric - layer imbalance - which defines the flatness of a solution. We demonstrate that different regularization methods, such as weight decay or noise data…

Machine Learning · Computer Science 2020-07-21 Boris Ginsburg

The high-dimensional features extracted from large-scale unlabeled data via various pretrained models with diverse architectures are referred to as heterogeneous multiview data. Most existing unsupervised transfer learning methods fail to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jie Chen , Yuanbiao Gou , Chuanbin Liu , Zhu Wang , Xi Peng

In distributed training of deep neural networks, people usually run Stochastic Gradient Descent (SGD) or its variants on each machine and communicate with other machines periodically. However, SGD might converge slowly in training some deep…

Machine Learning · Computer Science 2022-10-14 Mingrui Liu , Zhenxun Zhuang , Yunwei Lei , Chunyang Liao

Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators. In such…

Machine Learning · Computer Science 2026-05-29 Ruoran Xu , Borong She , Xiaobo Jin , Qiufeng Wang

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and…

Machine Learning · Computer Science 2026-04-21 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran

With the rapid development of conditional diffusion models, significant progress has been made in text-to-video generation. However, we observe that these models often neglect semantically important tokens during inference, leading to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Guoqing Zhang , Lu Shi , Wanru Xu , Linna Zhang , Sen Wang , Fangfang Wang , Yigang Cen

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

Machine Learning · Computer Science 2017-11-23 Haiping Huang , Taro Toyoizumi

Unsupervised domain adaptation aims to transfer rich knowledge from the annotated source domain to the unlabeled target domain with the same label space. One prevalent solution is the bi-discriminator domain adversarial network, which…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Chuang Zhao , Hongke Zhao , Hengshu Zhu , Zhenya Huang , Nan Feng , Enhong Chen , Hui Xiong

Sharpness-Aware Minimization (SAM) is an optimizer that takes a descent step based on the gradient at a perturbation $y_t = x_t + \rho \frac{\nabla f(x_t)}{\lVert \nabla f(x_t) \rVert}$ of the current point $x_t$. Existing studies prove…

Machine Learning · Computer Science 2023-10-30 Dongkuk Si , Chulhee Yun

Sharpness-Aware Minimization (SAM) has emerged as a powerful method for improving generalization in machine learning models by minimizing the sharpness of the loss landscape. However, despite its success, several important questions…

Optimization and Control · Mathematics 2025-03-05 Dimitris Oikonomou , Nicolas Loizou

By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algorithms will generally incur one extra forward-backward…

Machine Learning · Computer Science 2023-04-11 Yang Zhao , Hao Zhang , Xiuyuan Hu

Sharpness-aware minimization (SAM) methods have gained increasing popularity by formulating the problem of minimizing both loss value and loss sharpness as a minimax objective. In this work, we increase the efficiency of the maximization…

Machine Learning · Computer Science 2024-05-17 Gonçalo Mordido , Pranshu Malviya , Aristide Baratin , Sarath Chandar

We propose a new method for high-dimensional semi-supervised learning problems based on the careful aggregation of the results of a low-dimensional procedure applied to many axis-aligned random projections of the data. Our primary goal is…

Methodology · Statistics 2023-04-19 Tengyao Wang , Edgar Dobriban , Milana Gataric , Richard J. Samworth

Modern machine learning solutions require extensive data collection where labeling remains costly. To reduce this burden, open set active learning approaches aim to select informative samples from a large pool of unlabeled data that…

Machine Learning · Computer Science 2025-10-27 Young In Kim , Andrea Agiollo , Rajiv Khanna