English
Related papers

Related papers: Efficient Projection Algorithms onto the Weighted …

200 papers

In multi-objective optimization, multiple loss terms are weighted and added together to form a single objective. These weights are chosen to properly balance the competing losses according to some meta-goal. For example, in physics-informed…

Numerical Analysis · Mathematics 2025-11-20 Max Hirsch , Federico Pichi

Motivated by vision tasks such as robust face and object recognition, we consider the following general problem: given a collection of low-dimensional linear subspaces in a high-dimensional ambient (image) space, and a query point (image),…

Computer Vision and Pattern Recognition · Computer Science 2014-12-16 Ju Sun , Yuqian Zhang , John Wright

This paper considers a distributed stochastic strongly convex optimization, where agents connected over a network aim to cooperatively minimize the average of all agents' local cost functions. Due to the stochasticity of gradient estimation…

Optimization and Control · Mathematics 2020-02-17 Jinlong Lei , Peng Yi , Jie Chen , Yiguang Hong

Given a set of dissimilarity measurements amongst data points, determining what metric representation is most "consistent" with the input measurements or the metric that best captures the relevant geometric features of the data is a key…

Machine Learning · Computer Science 2022-09-28 Rishi Sonthalia , Anna C. Gilbert

The structured low-rank approximation problem for general affine structures, weighted 2-norms and fixed elements is considered. The variable projection principle is used to reduce the dimensionality of the optimization problem. Algorithms…

Optimization and Control · Mathematics 2013-07-26 Konstantin Usevich , Ivan Markovsky

The tensor-train (TT) format is a data-sparse tensor representation commonly used in high dimensional data approximations. In order to represent data with interpretability in data science, researchers develop data-centric skeletonized low…

Numerical Analysis · Mathematics 2026-02-10 Daniel Hayes , Jing-Mei Qiu , Tianyi Shi

Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and…

Machine Learning · Computer Science 2024-07-18 Jingyang Qiao , Zhizhong Zhang , Xin Tan , Yanyun Qu , Wensheng Zhang , Zhi Han , Yuan Xie

Several algorithms build on the perfect phylogeny model to infer evolutionary trees. This problem is particularly hard when evolutionary trees are inferred from the fraction of genomes that have mutations in different positions, across…

Data Structures and Algorithms · Computer Science 2018-12-31 Bei Jia , Surjyendu Ray , Sam Safavi , José Bento

Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Weicong Liang , Yuhui Yuan , Henghui Ding , Xiao Luo , Weihong Lin , Ding Jia , Zheng Zhang , Chao Zhang , Han Hu

Convolutional neural networks (CNNs) achieve remarkable performance in a wide range of fields. However, intensive memory access of activations introduces considerable energy consumption, impeding deployment of CNNs on resourceconstrained…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Yu-Shan Tai , Chieh-Fang Teng , Cheng-Yang Chang , An-Yeu Wu

In a series of recent works, we have generalised the consistency results in the stochastic block model literature to the case of uniform and non-uniform hypergraphs. The present paper continues the same line of study, where we focus on…

Machine Learning · Computer Science 2017-05-18 Debarghya Ghoshdastidar , Ambedkar Dukkipati

Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…

Computer Vision and Pattern Recognition · Computer Science 2017-02-07 Kota Hara , Raviteja Vemulapalli , Rama Chellappa

For regular Pareto Fronts (PFs), such as those that are smooth, continuous, and uniformly distributed, using fixed weight vectors is sufficient for multi-objective optimization approaches using decomposition. However, when encountering…

Neural and Evolutionary Computing · Computer Science 2025-11-18 Xiaojing Han , Yuanxin Li

A novel inline data compression method is presented for single-precision vectors in three dimensions. The primary application of the method is for accelerating computational physics calculations where the throughput is bound by memory…

Computational Engineering, Finance, and Science · Computer Science 2020-06-25 Will Trojak , Freddie Witherden

We study how much a linear program (LP) can be compressed when solved repeatedly, given prior knowledge about its objective function. Existing data-driven projection methods learn low-dimensional surrogate LPs with approximate…

Optimization and Control · Mathematics 2026-05-26 Yuhan Ye , Omar Bennouna

Object detection techniques that achieve state-of-the-art detection accuracy employ convolutional neural networks, implemented to have optimal performance in graphics processing units. Some hardware systems, such as mobile robots, operate…

Domain knowledge is useful to improve the generalization performance of learning machines. Sign constraints are a handy representation to combine domain knowledge with learning machine. In this paper, we consider constraining the signs of…

Machine Learning · Computer Science 2022-10-12 Kenya Tajima , Takahiko Henmi , Kohei Tsuchida , Esmeraldo Ronnie R. Zara , Tsuyoshi Kato

Label prediction in neural networks (NNs) has O(n) complexity proportional to the number of classes. This holds true for classification using fully connected layers and cosine similarity with some set of class prototypes. In this paper we…

Machine Learning · Computer Science 2026-04-07 Nikita Gabdullin , Ilya Androsov

We propose a new method for simplification of Gaussian process (GP) models by projecting the information contained in the full encompassing model and selecting a reduced number of variables based on their predictive relevance. Our results…

Methodology · Statistics 2017-12-18 Juho Piironen , Aki Vehtari

Seeking informative projecting directions has been an important task in utilizing sliced Wasserstein distance in applications. However, finding these directions usually requires an iterative optimization procedure over the space of…

Machine Learning · Statistics 2022-09-26 Khai Nguyen , Nhat Ho