English
Related papers

Related papers: Lifelong Learning with Sketched Structural Regular…

200 papers

The structural re-parameterization (SRP) technique is a novel deep learning technique that achieves interconversion between different network architectures through equivalent parameter transformations. This technique enables the mitigation…

Computer Vision and Pattern Recognition · Computer Science 2024-08-08 Shanshan Zhong , Zhongzhan Huang , Wushao Wen , Jinghui Qin , Liang Lin

Generalized matrix approximation plays a fundamental role in many machine learning problems, such as CUR decomposition, kernel approximation, and matrix low rank approximation. Especially with today's applications involved in larger and…

Numerical Analysis · Computer Science 2016-09-09 Haishan Ye , Qiaoming Ye , Zhihua Zhang

The ability to learn different tasks sequentially is essential to the development of artificial intelligence. In general, neural networks lack this capability, the major obstacle being catastrophic forgetting. It occurs when the…

Machine Learning · Computer Science 2021-10-22 Kaustubh Olpadkar , Ekta Gavas

Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task. This issue arises due to the model's tendency to overwrite previously acquired knowledge with new…

Machine Learning · Computer Science 2025-12-02 Lama Alssum , Hasan Abed Al Kader Hammoud , Motasem Alfarra , Juan C Leon Alcazar , Bernard Ghanem

Complex structures are typical in machine learning. Tailoring learning algorithms for every structure requires an effort that may be saved by defining a generic learning procedure adaptive to any complex structure. In this paper, we propose…

Machine Learning · Computer Science 2019-05-28 Pablo Strasser , Stephane Armand , Stephane Marchand-Maillet , Alexandros Kalousis

Numerical computations involving rational matrices often benefit from preserving underlying matrix structures such as symmetry, Hermitian properties, or sparsity that reflect physical, geometric, or algebraic characteristics of the system.…

Rings and Algebras · Mathematics 2026-02-26 Avisek Bist , Namita Behera

Catastrophic forgetting remains a major challenge for continual learning (CL) in automatic speech recognition (ASR), where models must adapt to new domains without losing performance on previously learned conditions. Several CL methods have…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-14 Steven Vander Eeckt , Hugo Van hamme

The persistent challenge of catastrophic forgetting in neural networks has motivated extensive research in continual learning . This work presents a novel continual learning framework that integrates Fisher-weighted asymmetric…

Machine Learning · Computer Science 2025-08-26 Krisanu Sarkar

Structured low-rank (SLR) algorithms, which exploit annihilation relations between the Fourier samples of a signal resulting from different properties, is a powerful image reconstruction framework in several applications. This scheme relies…

Machine Learning · Computer Science 2020-08-11 Aniket Pramanik , Hemant Aggarwal , Mathews Jacob

We propose a new randomized algorithm for solving L2-regularized least-squares problems based on sketching. We consider two of the most popular random embeddings, namely, Gaussian embeddings and the Subsampled Randomized Hadamard Transform…

Machine Learning · Computer Science 2020-10-26 Jonathan Lacotte , Mert Pilanci

Matrices arising in scientific applications frequently admit linear low-rank approximations due to smoothness in the physical and/or temporal domain of the problem. In large-scale problems, computing an optimal low-rank approximation can be…

Numerical Analysis · Mathematics 2021-05-05 Alec Michael Dunton , Alireza Doostan

We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design…

Machine Learning · Computer Science 2017-07-31 Carlo Ciliberto , Alessandro Rudi , Lorenzo Rosasco

We consider a continual learning (CL) problem with two linear regression tasks in the fixed design setting, where the feature vectors are assumed fixed and the labels are assumed to be random variables. We consider an $\ell_2$-regularized…

Machine Learning · Computer Science 2024-06-19 Haoran Li , Jingfeng Wu , Vladimir Braverman

Regularization is an effective way to promote the generalization performance of machine learning models. In this paper, we focus on label smoothing, a form of output distribution regularization that prevents overfitting of a neural network…

Machine Learning · Computer Science 2020-07-07 Weizhi Li , Gautam Dasarathy , Visar Berisha

Many relevant machine learning and scientific computing tasks involve high-dimensional linear operators accessible only via costly matrix-vector products. In this context, recent advances in sketched methods have enabled the construction of…

Machine Learning · Computer Science 2025-10-03 Andres Fernandez , Felix Dangel , Philipp Hennig , Frank Schneider

Regularization techniques are widely employed in optimization-based approaches for solving ill-posed inverse problems in data analysis and scientific computing. These methods are based on augmenting the objective with a penalty function,…

Optimization and Control · Mathematics 2021-06-08 Yong Sheng Soh , Venkat Chandrasekaran

We introduce a novel stochastic regularization technique for deep neural networks, which decomposes a layer into multiple branches with different parameters and merges stochastically sampled combinations of the outputs from the branches…

Machine Learning · Computer Science 2019-10-04 Wonpyo Park , Paul Hongsuck Seo , Bohyung Han , Minsu Cho

A methodology for using random sketching in the context of model order reduction for high-dimensional parameter-dependent systems of equations was introduced in [Balabanov and Nouy 2019, Part I]. Following this framework, we here construct…

Numerical Analysis · Mathematics 2022-03-25 Oleg Balabanov , Anthony Nouy

We introduce a "learning-based" algorithm for the low-rank decomposition problem: given an $n \times d$ matrix $A$, and a parameter $k$, compute a rank-$k$ matrix $A'$ that minimizes the approximation loss $\|A-A'\|_F$. The algorithm uses a…

Machine Learning · Computer Science 2019-10-31 Piotr Indyk , Ali Vakilian , Yang Yuan

Reinforcement learning (RL) is increasingly applied to real-world problems involving complex and structured decisions, such as routing, scheduling, and assortment planning. These settings challenge standard RL algorithms, which struggle to…

Machine Learning · Computer Science 2025-10-29 Heiko Hoppe , Léo Baty , Louis Bouvier , Axel Parmentier , Maximilian Schiffer