Results 21 to 30 of about 12,418,444 (305)
Language model compression with weighted low-rank factorization [PDF]
International Conference on Learning Representations, 2022 Factorizing a large matrix into small matrices is a popular strategy for model compression. Singular value decomposition (SVD) plays a vital role in this compression strategy, approximating a learned matrix with fewer parameters.
Yen-Chang Hsu +5 more
semanticscholar +1 more source
A Remote Sensing Image Destriping Model Based on Low-Rank and Directional Sparse Constraint
Remote Sensing, 2021 Stripe noise is a common condition that has a considerable impact on the quality of the images. Therefore, stripe noise removal (destriping) is a tremendously important step in image processing.
Xiaobin Wu +4 more
doaj +1 more source
International Journal of Coal Science & Technology, 2017 Benzene carboxylic acid (BCAs) are common and useful chemical blocks, which can be derived from the abundant low rank coals (LRCs) via oxidative degradation. In this work, we proposed a novel strategy to utilize BCAs as raw materials to prepare catalysts
Huacong Zhou +8 more
doaj +1 more source
Low-Rank Autoregressive Tensor Completion for Spatiotemporal Traffic Data Imputation [PDF]
IEEE transactions on intelligent transportation systems (Print), 2021 Spatiotemporal traffic time series (e.g., traffic volume/speed) collected from sensing systems are often incomplete with considerable corruption and large amounts of missing values, preventing users from harnessing the full power of the data.
Xinyu Chen +3 more
semanticscholar +1 more source
Efficient Low-rank Multimodal Fusion With Modality-Specific Factors [PDF]
Annual Meeting of the Association for Computational Linguistics, 2018 Multimodal research is an emerging field of artificial intelligence, and one of the main research problems in this field is multimodal fusion. The fusion of multimodal data is the process of integrating multiple unimodal representations into one compact ...
Zhun Liu +5 more
semanticscholar +1 more source
Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 Since higher-order tensors are naturally suitable for representing multi-dimensional data in real-world, e.g., color images and videos, low-rank tensor representation has become one of the emerging areas in machine learning and computer vision.
Yisi Luo +4 more
semanticscholar +1 more source
Non-Negative Low Rank Graph Embedding Algorithm
Jisuanji kexue yu tansuo, 2020 The existing non-negative matrix factorization (NMF) algorithms still have some shortcomings. On one hand, the NMF method calculates its low-dimensional representation directly on the high-dimensional original image data set, but in fact the effective ...
LIU Guoqing, LU Guifu, ZHOU Sheng, XUAN Dongdong, CAO Along
doaj +1 more source
Randomized Rank-Revealing QLP for Low-Rank Matrix Decomposition
IEEE Access, 2023 The pivoted QLP decomposition is computed through two consecutive pivoted QR decompositions. It is an approximation to the computationally prohibitive singular value decomposition (SVD). This work is concerned with a partial QLP decomposition of matrices
Maboud F. Kaloorazi +4 more
doaj +1 more source
InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning [PDF]
Computer Vision and Pattern RecognitionContinual learning requires the model to learn multiple tasks sequentially. In continual learning, the model should possess the ability to maintain its performance on old tasks (stability) and the ability to adapt to new tasks continuously (plasticity ...
Yan-Shuo Liang, Wu-Jun Li
semanticscholar +1 more source
Low rank multivariate regression [PDF]
Electronic Journal of Statistics, 2011 We consider in this paper the multivariate regression problem, when the target regression matrix $A$ is close to a low rank matrix. Our primary interest in on the practical case where the variance of the noise is unknown. Our main contribution is to propose in this setting a criterion to select among a family of low rank estimators and prove a non ...
openaire +3 more sources