English
Related papers

Related papers: Training Without Orthogonalization, Inference With…

200 papers

Deep operator networks (DeepONets) are powerful architectures for fast and accurate emulation of complex dynamics. As their remarkable generalization capabilities are primarily enabled by their projection-based attribute, we investigate…

Machine Learning · Computer Science 2022-11-15 Simone Venturi , Tiernan Casey

This paper analyzes the robustness of recent 3D shape descriptors to SO(3) rotations, something that is fundamental to shape modeling. Specifically, we formulate the task of rotated 3D object instance detection. To do so, we consider a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-31 Supriya Gadi Patil , Angel X. Chang , Manolis Savva

PGD adversarial training, the standard robustness method, can reduce Jacobian Frobenius norm yet worsen clean-input geometry (e.g., TDI 1.336 vs. ERM 1.093). We show this is not an implementation artifact but a theorem-level consequence of…

Machine Learning · Computer Science 2026-04-28 Vishal Rajput

We propose a novel variant of SGD customized for training network architectures that support anytime behavior: such networks produce a series of increasingly accurate outputs over time. Efficient architectural designs for these networks…

Machine Learning · Computer Science 2020-08-18 Chengcheng Wan , Henry Hoffmann , Shan Lu , Michael Maire

Differential privacy (DP) protects sensitive data during neural network training, but standard methods like DP-Adam suffer from high memory overhead due to per-sample gradient clipping, limiting scalability. We introduce DP-GRAPE (Gradient…

Machine Learning · Computer Science 2026-05-19 Alex Mulrooney , Devansh Gupta , James Flemings , Huanyu Zhang , Murali Annavaram , Meisam Razaviyayn , Xinwei Zhang

The optimization algorithms are crucial in training physics-informed neural networks (PINNs), as unsuitable methods may lead to poor solutions. Compared to the common gradient descent (GD) algorithm, implicit gradient descent (IGD)…

Machine Learning · Computer Science 2025-08-04 Xianliang Xu , Ting Du , Wang Kong , Bin Shan , Ye Li , Zhongyi Huang

Stochastic gradient descent (SGD) is the optimization algorithm of choice in many machine learning applications such as regularized empirical risk minimization and training deep neural networks. The classical convergence analysis of SGD is…

Optimization and Control · Mathematics 2018-07-10 Lam M. Nguyen , Phuong Ha Nguyen , Marten van Dijk , Peter Richtárik , Katya Scheinberg , Martin Takáč

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

Representing images and videos with Symmetric Positive Definite (SPD) matrices, and considering the Riemannian geometry of the resulting space, has been shown to yield high discriminative power in many visual recognition tasks.…

Computer Vision and Pattern Recognition · Computer Science 2016-05-23 Mehrtash Harandi , Mathieu Salzmann , Richard Hartley

Orthogonal drawings, i.e., embeddings of graphs into grids, are a classic topic in Graph Drawing. Often the goal is to find a drawing that minimizes the number of bends on the edges. A key ingredient for bend minimization algorithms is the…

Computational Geometry · Computer Science 2019-03-13 Benjamin Niedermann , Ignaz Rutter , Matthias Wolf

In this paper, we address the problem of 6-DoF object pose estimation from a single RGB image. Indirect methods that typically predict intermediate 2D keypoints, followed by a Perspective-n-Point solver, have shown great performance. Direct…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Nassim Ali Ousalah , Peyman Rostami , Vincent Gaudillière , Emmanuel Koumandakis , Anis Kacem , Enjie Ghorbel , Djamila Aouada

Stochastic Gradient Descent (SGD) and its variants are the most used algorithms in machine learning applications. In particular, SGD with adaptive learning rates and momentum is the industry standard to train deep networks. Despite the…

Machine Learning · Statistics 2020-07-29 Xiaoyu Li , Francesco Orabona

Orthonormality is the foundation of matrix decomposition. For example, Singular Value Decomposition (SVD) implements the compression by factoring a matrix with orthonormal parts and is pervasively utilized in various fields. Orthonormality,…

Data Structures and Algorithms · Computer Science 2021-12-08 Huiwen Wang , Yanwen Zhang , Jichang Zhao

Subgradient algorithms for training support vector machines have been quite successful for solving large-scale and online learning problems. However, they have been restricted to linear kernels and strongly convex formulations. This paper…

Machine Learning · Computer Science 2011-11-04 Sangkyun Lee , Stephen J. Wright

While large machine learning models have shown remarkable performance in various domains, their training typically requires iterating for many passes over the training data. However, due to computational and memory constraints and potential…

Machine Learning · Computer Science 2025-11-04 Youngjae Min , Namhoon Cho , Navid Azizan

While stochastic gradient descent (SGD) is still the most popular optimization algorithm in deep learning, adaptive algorithms such as Adam have established empirical advantages over SGD in some deep learning applications such as training…

Machine Learning · Computer Science 2023-06-02 Yan Pan , Yuanzhi Li

This article examines the implicit regularization effect of Stochastic Gradient Descent (SGD). We consider the case of SGD without replacement, the variant typically used to optimize large-scale neural networks. We analyze this algorithm in…

Machine Learning · Computer Science 2024-04-23 Pierfrancesco Beneventano

We revisit the use of Stochastic Gradient Descent (SGD) for solving convex optimization problems that serve as highly popular convex relaxations for many important low-rank matrix recovery problems such as \textit{matrix completion},…

Machine Learning · Computer Science 2020-06-16 Dan Garber

Symmetric objects are common in daily life and industry, yet their inherent orientation ambiguities that impede the training of deep learning networks for pose estimation are rarely discussed in the literature. To cope with these…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Andreas Kriegler , Csaba Beleznai , Margrit Gelautz

Singular value decomposition (SVD) is one of the most popular compression methods that approximate a target matrix with smaller matrices. However, standard SVD treats the parameters within the matrix with equal importance, which is a simple…

Computation and Language · Computer Science 2022-12-19 Ting Hua , Yen-Chang Hsu , Felicity Wang , Qian Lou , Yilin Shen , Hongxia Jin