English
Related papers

Related papers: Explicit Eigenvalue Regularization Improves Sharpn…

200 papers

Decentralized stochastic gradient descent (D-SGD) allows collaborative learning on massive devices simultaneously without the control of a central server. However, existing theories claim that decentralization invariably undermines…

Machine Learning · Computer Science 2023-11-10 Tongtian Zhu , Fengxiang He , Kaixuan Chen , Mingli Song , Dacheng Tao

Image segmentation is an inherently ill-posed problem and thus requires regularization in order to limit the search space to reasonable solutions. A majority of segmentation methods integrates these regularization terms in one way or the…

Numerical Analysis · Mathematics 2018-10-31 Uri Nahum , Philippe C. Cattin

Recently, researchers observed that gradient descent for deep neural networks operates in an ``edge-of-stability'' (EoS) regime: the sharpness (maximum eigenvalue of the Hessian) is often larger than stability threshold $2/\eta$ (where…

Machine Learning · Computer Science 2023-02-22 Xingyu Zhu , Zixuan Wang , Xiang Wang , Mo Zhou , Rong Ge

Black-box optimization algorithms have been widely used in various machine learning problems, including reinforcement learning and prompt fine-tuning. However, directly optimizing the training loss value, as commonly done in existing…

Machine Learning · Computer Science 2024-10-17 Feiyang Ye , Yueming Lyu , Xuehao Wang , Masashi Sugiyama , Yu Zhang , Ivor Tsang

Semi-supervised learning has attracted much attention due to its less dependence on acquiring abundant annotations from experts compared to fully supervised methods, which is especially important for medical image segmentation which…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Yichi Zhang , Jin Yang , Yuchen Liu , Yuan Cheng , Yuan Qi

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

Regularization is a powerful technique for extracting useful information from noisy data. Typically, it is implemented by adding some sort of norm constraint to an objective function and then exactly optimizing the modified objective…

Data Structures and Algorithms · Computer Science 2011-04-28 Michael W. Mahoney , Lorenzo Orecchia

Toward achieving robust and defensive neural networks, the robustness against the weight parameters perturbations, i.e., sharpness, attracts attention in recent years (Sun et al., 2020). However, sharpness is known to remain a critical…

Machine Learning · Computer Science 2021-06-29 Hikaru Ibayashi , Takuo Hamaguchi , Masaaki Imaizumi

Sharpness-aware minimization (SAM) reports improving domain generalization by reducing the loss surface curvature in the parameter space. However, generalization during fine-tuning is often more dependent on the transferability of…

Machine Learning · Computer Science 2024-03-13 Tom Sherborne , Naomi Saphra , Pradeep Dasigi , Hao Peng

Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but they perform suboptimally on remote sensing imagery (RSI) due to severe domain shifts and the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 M. Naseer Subhani

Long-tail learning has garnered widespread attention and achieved significant progress in recent times. However, even with pre-trained prior knowledge, models still exhibit weaker generalization performance on tail classes. The promising…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Mengke Li , Ye Liu , Yang Lu , Yiqun Zhang , Yiu-ming Cheung , Hui Huang

Optimization in Deep Learning is mainly dominated by first-order methods which are built around the central concept of backpropagation. Second-order optimization methods, which take into account the second-order derivatives are far less…

Machine Learning · Computer Science 2021-04-09 Fares B. Mehouachi , Chaouki Kasmi

Learning from Noisy Labels (LNL) remains a fundamental challenge in deep learning because real-world datasets often contain corrupted annotations. Most existing methods rely on label correction or sample selection mechanisms. In contrast,…

Machine Learning · Computer Science 2026-05-29 Jiayu Xu , Junbiao Pang

The largest eigenvalue of the Hessian, or sharpness, of neural networks is a key quantity to understand their optimization dynamics. In this paper, we study the sharpness of deep linear networks for univariate regression. Minimizers can…

Machine Learning · Statistics 2024-10-29 Pierre Marion , Lénaïc Chizat

We develop regularization methods to find flat minima while training deep neural networks. These minima generalize better than sharp minima, yielding models outperforming baselines on real-world test data (which may be distributed…

Machine Learning · Computer Science 2025-07-04 Adam Sandler , Diego Klabjan , Yuan Luo

Recent work has shown that methods like SAM which either explicitly or implicitly penalize second order information can improve generalization in deep learning. Seemingly similar methods like weight noise and gradient penalties often fail…

Machine Learning · Computer Science 2024-01-26 Yann N. Dauphin , Atish Agarwala , Hossein Mobahi

Sparsity in the eigenvectors of signal covariance matrices is exploited in this paper for compression and denoising. Dimensionality reduction (DR) and quantization modules present in many practical compression schemes such as transform…

Applications · Statistics 2015-06-03 Ioannis D. Schizas , Georgios B. Giannakis

Second-order Latent Factor (SLF) model, a class of low-rank representation learning methods, has proven effective at extracting node-to-node interaction patterns from High-dimensional and Incomplete (HDI) data. However, its optimization is…

Machine Learning · Computer Science 2025-12-19 Jialiang Wang , Xueyan Bao , Hao Wu

Understanding the geometry of the loss landscape near a minimum is key to explaining the implicit bias of gradient-based methods in non-convex optimization problems such as deep neural network training and deep matrix factorization. A…

Machine Learning · Statistics 2026-02-05 Anil Kamber , Rahul Parhi

Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Zijia Wang , Wenbin Yang , Zhisong Liu , Zhen Jia