English
Related papers

Related papers: Operator SVD with Neural Networks via Nested Low-R…

200 papers

A common technique for compressing a neural network is to compute the $k$-rank $\ell_2$ approximation $A_{k,2}$ of the matrix $A\in\mathbb{R}^{n\times d}$ that corresponds to a fully connected layer (or embedding layer). Here, $d$ is the…

Machine Learning · Computer Science 2020-09-29 Murad Tukan , Alaa Maalouf , Matan Weksler , Dan Feldman

When applying eigenvalue decomposition on the quadratic term matrix in a type of linear equally constrained quadratic programming (EQP), there exists a linear mapping to project optimal solutions between the new EQP formulation where $Q$ is…

Optimization and Control · Mathematics 2020-10-22 Shi Yu

In the field of large language model (LLM) compression, singular value decomposition (SVD) is a widely studied and adopted low-rank decomposition technique. Since SVD operates exclusively on linear modules, and these modules in LLMs are…

Machine Learning · Computer Science 2025-10-23 Lin Xv , Jingsheng Gao , Xian Gao , Ting Liu , Yuzhuo Fu

Nonlinear phenomena can be analyzed via linear techniques using operator-theoretic approaches. Data-driven method called the extended dynamic mode decomposition (EDMD) and its variants, which approximate the Koopman operator associated with…

Machine Learning · Computer Science 2022-05-18 Hiroaki Terao , Sho Shirasaka , Hideyuki Suzuki

Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned for a specific downstream task. The most common fine-tuning method is to update pretrained weights via low-rank adaptation (LoRA). Existing initialization…

Machine Learning · Computer Science 2025-10-21 Fabian Paischer , Lukas Hauzenberger , Thomas Schmied , Benedikt Alkin , Marc Peter Deisenroth , Sepp Hochreiter

Tensor completion and robust principal component analysis have been widely used in machine learning while the key problem relies on the minimization of a tensor rank that is very challenging. A common way to tackle this difficulty is to…

Machine Learning · Computer Science 2021-05-26 Tao Li , Jinwen Ma

We study the problem of finding structured low-rank matrices using nuclear norm regularization where the structure is encoded by a linear map. In contrast to most known approaches for linearly structured rank minimization, we do not (a) use…

Systems and Control · Computer Science 2015-09-09 Adams Wei Yu , Wanli Ma , Yaoliang Yu , Jaime G. Carbonell , Suvrit Sra

The incremental singular value decomposition (SVD) updates a truncated SVD as new columns arrive, replacing a single large SVD with a sequence of small ones. In floating-point arithmetic, each update multiplies the running singular basis by…

Numerical Analysis · Mathematics 2026-05-05 Yangwen Zhang

To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank…

Computer Vision and Pattern Recognition · Computer Science 2020-01-27 Yuhui Xu , Yuxi Li , Shuai Zhang , Wei Wen , Botao Wang , Wenrui Dai , Yingyong Qi , Yiran Chen , Weiyao Lin , Hongkai Xiong

Recent advances in representation learning reveal that widely used objectives, such as contrastive and non-contrastive, implicitly perform spectral decomposition of a contextual kernel, induced by the relationship between inputs and their…

Machine Learning · Computer Science 2025-10-29 Burak Varıcı , Che-Ping Tsai , Ritabrata Ray , Nicholas M. Boffi , Pradeep Ravikumar

In this paper we propose efficient randomized fixed-precision techniques for low tubal rank approximation of tensors. The proposed methods are faster and more efficient than the existing fixed-precision algorithms for approximating the…

Numerical Analysis · Mathematics 2025-05-22 Salman Ahmadi-Asl , Naeim Rezaeian , Cesar F. Caiafa , Andre L. F. de Almeidad

A new variational mode decomposition (VMD) based deep learning approach is proposed in this paper for time series forecasting problem. Firstly, VMD is adopted to decompose the original time series into several sub-signals. Then, a…

Machine Learning · Statistics 2020-02-25 Guowei Zhang , Tao Ren , Yifan Yang

Deep neural networks (DNNs) have achieved remarkable success in computer vision; however, training DNNs for satisfactory performance remains challenging and suffers from sensitivity to empirical selections of an optimization algorithm for…

Computer Vision and Pattern Recognition · Computer Science 2020-12-22 Haichao Zhang , Kuangrong Hao , Lei Gao , Bing Wei , Xuesong Tang

A neural network regularizer (e.g., weight decay) boosts performance by explicitly penalizing the complexity of a network. In this paper, we penalize inferior network activations -- feature embeddings -- which in turn regularize the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Ahmed Taha , Alex Hanson , Abhinav Shrivastava , Larry Davis

Cartoon-texture image decomposition is a critical preprocessing problem bottlenecked by the numerical intractability of classical variational or optimization models and the tedious manual tuning of global regularization parameters.We…

Numerical Analysis · Mathematics 2026-01-09 Alessandro Lanza , Serena Morigi , Youwei Wen , Li Yang

Eigensystem Realization Algorithm (ERA) is a data-driven approach for subspace system identification and is widely used in many areas of engineering. However, the computational cost of the ERA is dominated by a step that involves the…

Numerical Analysis · Mathematics 2020-11-03 Rachel Minster , Arvind K. Saibaba , Jishnudeep Kar , Aranya Chakrabortty

Symmetric orthogonalization via SVD, and closely related procedures, are well-known techniques for projecting matrices onto $O(n)$ or $SO(n)$. These tools have long been used for applications in computer vision, for example optimal 3D…

Computer Vision and Pattern Recognition · Computer Science 2020-06-26 Jake Levinson , Carlos Esteves , Kefan Chen , Noah Snavely , Angjoo Kanazawa , Afshin Rostamizadeh , Ameesh Makadia

A method for approximating sixth-order ordinary differential equations is proposed, which utilizes a deep learning feedforward artificial neural network, referred to as a neural solver. The efficacy of this unsupervised machine learning…

Numerical Analysis · Mathematics 2025-09-16 Janavi Bhalala , B. Veena S. N. Rao

In this article, we consider the sparse tensor singular value decomposition, which aims for dimension reduction on high-dimensional high-order data with certain sparsity structure. A method named Sparse Tensor Alternating Thresholding for…

Statistics Theory · Mathematics 2024-07-09 Anru Zhang , Rungang Han

Training deep neural networks (DNNs) with backpropagation (BP) achieves state-of-the-art accuracy but requires global error propagation and full parameterization, leading to substantial memory and computational overhead. Direct Feedback…

Machine Learning · Computer Science 2025-10-30 Arani Roy , Marco P. Apolinario , Shristi Das Biswas , Kaushik Roy