English
Related papers

Related papers: Training Without Orthogonalization, Inference With…

200 papers

Various pose estimation and tracking problems in robotics can be decomposed into a correspondence estimation problem (often computed using a deep network) followed by a weighted least squares optimization problem to solve for the poses.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Swaminathan Gurumurthy , Karnik Ram , Bingqing Chen , Zachary Manchester , Zico Kolter

Recent work on visual representation learning has shown to be efficient for robotic manipulation tasks. However, most existing works pretrained the visual backbone solely on 2D images or egocentric videos, ignoring the fact that robots…

Stochastic gradient descent (SGD) is the workhorse of modern machine learning. Sometimes, there are many different potential gradient estimators that can be used. When so, choosing the one with the best tradeoff between cost and variance is…

Machine Learning · Computer Science 2020-10-23 Tomas Geffner , Justin Domke

In large-scale time series forecasting, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset. In this paper, we provably show under such…

Machine Learning · Computer Science 2021-06-14 Yucheng Lu , Youngsuk Park , Lifan Chen , Yuyang Wang , Christopher De Sa , Dean Foster

Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the dynamics of stochastic gradient descent over diagonal linear…

Machine Learning · Computer Science 2021-12-08 Scott Pesme , Loucas Pillaud-Vivien , Nicolas Flammarion

Vision Transformers (ViT) have been established as large-scale foundation models. However, because self-attention operates globally, they lack an explicit mechanism to distinguish foreground from background. As a result, ViT may learn…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Haruhiko Murata , Kazuhiro Hotta

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Machine Learning · Computer Science 2020-06-11 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi

Gradient dominance property is a condition weaker than strong convexity, yet sufficiently ensures global convergence even in non-convex optimization. This property finds wide applications in machine learning, reinforcement learning (RL),…

Optimization and Control · Mathematics 2024-05-30 Jiyuan Tan , Chenyu Xue , Chuwen Zhang , Qi Deng , Dongdong Ge , Yinyu Ye

Self-supervised learning for pre-training (SSP) can help the network learn better low-level features, especially when the size of the training set is small. In contrastive pre-training, the network is pre-trained to distinguish between…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Amy Saranchuk , Michael Guerzhoy

Accurate 6D object pose estimation is fundamental to robotic manipulation and grasping. Previous methods follow a local optimization approach which minimizes the distance between closest point pairs to handle the rotation ambiguity of…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Meng Tian , Liang Pan , Marcelo H Ang , Gim Hee Lee

Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches. Most state-of-the-art methods enforce similarity…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Sravanti Addepalli , Kaushal Bhogale , Priyam Dey , R. Venkatesh Babu

Estimating matrices in the symmetric positive-definite (SPD) cone is of interest for many applications ranging from computer vision to graph learning. While there exist various convex optimization-based estimators, they remain limited in…

Machine Learning · Computer Science 2025-03-24 Can Pouliquen , Mathurin Massias , Titouan Vayer

Inspired by dynamic programming, we propose Stochastic Virtual Gradient Descent (SVGD) algorithm where the Virtual Gradient is defined by computational graph and automatic differentiation. The method is computationally efficient and has…

Machine Learning · Computer Science 2019-08-01 Zheng Li , Shi Shu

While data augmentation is widely used to train symmetry-agnostic models, it remains unclear how quickly and effectively they learn to respect symmetries. We investigate this by deriving a principled measure of equivariance error that, for…

Machine Learning · Computer Science 2025-12-03 Max W. Shen , Ewa Nowara , Michael Maser , Kyunghyun Cho

This paper revisits the convergence of Stochastic Mirror Descent (SMD) in the contemporary nonconvex optimization setting. Existing results for batch-free nonconvex SMD restrict the choice of the distance generating function (DGF) to be…

Optimization and Control · Mathematics 2024-02-28 Ilyas Fatkhullin , Niao He

Stochastic Gradient Descent (SGD) is arguably the most important single algorithm in modern machine learning. Although SGD with unbiased gradient estimators has been studied extensively over at least half a century, SGD variants relying on…

Machine Learning · Computer Science 2023-05-26 Yury Demidovich , Grigory Malinovsky , Igor Sokolov , Peter Richtárik

In this paper, we introduce a model for analyzing deep learning optimization over a single iteration by leveraging the matrix structure of the weights. We derive the model by assuming isotropy of curvature, including the second-order…

Optimization and Control · Mathematics 2025-11-04 Weijie Su

Recent progress in object pose prediction provides a promising path for robots to build object-level scene representations during navigation. However, as we deploy a robot in novel environments, the out-of-distribution data can degrade the…

Robotics · Computer Science 2022-08-17 Ziqi Lu , Yihao Zhang , Kevin Doherty , Odin Severinsen , Ethan Yang , John Leonard

Machine unlearning aims to remove the influence of problematic training data after a model has been trained. The primary challenge in machine unlearning is ensuring that the process effectively removes specified data without compromising…

Machine Learning · Computer Science 2026-03-10 Aviv Shamsian , Eitan Shaar , Aviv Navon , Gal Chechik , Ethan Fetaya

The aim of this paper is to deepen the convergence analysis of the scaled gradient projection (SGP) method, proposed by Bonettini et al. in a recent paper for constrained smooth optimization. The main feature of SGP is the presence of a…

Numerical Analysis · Mathematics 2015-09-10 Silvia Bonettini , Marco Prato