English
Related papers

Related papers: OSDN: Improving Delta Rule with Provable Online Pr…

200 papers

We establish convergence of the training dynamics of residual neural networks (ResNets) to their joint infinite depth L, hidden width M, and embedding dimension D limit. Specifically, we consider ResNets with two-layer perceptron blocks in…

Machine Learning · Statistics 2026-03-23 Louis-Pierre Chaintron , Lénaïc Chizat , Javier Maass

Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compute linearly during inference. A recent stream of work…

We consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function (comparator) in hindsight. Popular algorithms in this…

Machine Learning · Computer Science 2019-02-21 Michał Kempka , Wojciech Kotłowski , Manfred K. Warmuth

Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexity of standard softmax attention. Existing methods perform token routing based on…

Machine Learning · Computer Science 2026-02-03 Weikang Meng , Liangyu Huo , Yadan Luo , Jiawen Guan , Jingyi Zhang , Yingjian Li , Zheng Zhang

The paradigm of large language model (LLM) reasoning is shifting from parameter scaling to test-time compute scaling, yet many existing approaches still rely on uniform brute-force sampling (for example, fixed best-of-N or self-consistency)…

Artificial Intelligence · Computer Science 2026-03-02 Siyuan Ma , Bo Gao , Xiaojun Jia , Simeng Qin , Tianlin Li , Ke Ma , Xiaoshuang Jia , Wenqi Ren , Yang Liu

Subset selection for the rank $k$ approximation of an $n\times d$ matrix $A$ offers improvements in the interpretability of matrices, as well as a variety of computational savings. This problem is well-understood when the error measure is…

Data Structures and Algorithms · Computer Science 2023-04-20 David P. Woodruff , Taisuke Yasuda

Automated segmentation of structural defects from visual inspection imagery remains challenging due to the diversity of damage types, extreme class imbalance, and the need for precise boundary delineation. This paper presents DeltaSeg, a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Enrique Hernandez Noguera , Md Meftahul Ferdaus , Elias Ioup , Mahdi Abdelguerfi

Deep reinforcement learning (DRL) has shown incredible performance in learning various tasks to the human level. However, unlike human perception, current DRL models connect the entire low-level sensory input to the state-action values…

Machine Learning · Computer Science 2017-12-14 Jinyoung Choi , Beom-Jin Lee , Byoung-Tak Zhang

Recent advances in text recognition led to a paradigm shift for page-level recognition, from multi-step segmentation-based approaches to end-to-end attention-based ones. However, the na\"ive character-level autoregressive decoding process…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Denis Coquenet

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they…

Machine Learning · Computer Science 2025-06-18 Yeonju Ro , Zhenyu Zhang , Souvik Kundu , Zhangyang Wang , Aditya Akella

In contrast to offline working fashions, two research paradigms are devised for online learning: (1) Online Meta Learning (OML) learns good priors over model parameters (or learning to learn) in a sequential setting where tasks are revealed…

Machine Learning · Computer Science 2021-08-24 Chen Zhao , Feng Chen , Bhavani Thuraisingham

Optical Character Recognition (OCR) is essential in applications such as document processing, license plate recognition, and intelligent surveillance. However, existing OCR models often underperform in real-world scenarios due to irregular…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Inho Jake Park , Jaehoon Jay Jeong , Ho-Sang Jo

Softmax-based dot-product attention is a cornerstone of Transformer architectures, enabling remarkable capabilities such as in-context learning. However, as context lengths increase, a fundamental limitation of the softmax function emerges:…

Machine Learning · Computer Science 2026-02-12 Sai Surya Duvvuri , Nirmal Patel , Nilesh Gupta , Inderjit S. Dhillon

Edge computing scenarios necessitate the development of hardware-efficient online continual learning algorithms to be adaptive to dynamic environment. However, existing algorithms always suffer from high memory overhead and bias towards…

Neural and Evolutionary Computing · Computer Science 2025-10-17 Erliang Lin , Wenbin Luo , Wei Jia , Yu Chen , Shaofu Yang

LiDAR-based place recognition is one of the key components of SLAM and global localization in autonomous vehicles and robotics applications. With the success of DL approaches in learning useful information from 3D LiDARs, place recognition…

Computer Vision and Pattern Recognition · Computer Science 2023-01-05 Tiago Barros , Luís Garrote , Ricardo Pereira , Cristiano Premebida , Urbano J. Nunes

Structural credit assignment for recurrent learning is challenging. An algorithm called RTRL can compute gradients for recurrent networks online but is computationally intractable for large networks. Alternatives, such as BPTT, are not…

Machine Learning · Computer Science 2021-03-11 Khurram Javed , Martha White , Rich Sutton

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

The Laplace approximation provides a closed-form model selection objective for neural networks (NN). Online variants, which optimise NN parameters jointly with hyperparameters, like weight decay strength, have seen renewed interest in the…

Machine Learning · Computer Science 2024-01-10 Jihao Andreas Lin , Javier Antorán , José Miguel Hernández-Lobato

Various deep neural network architectures (DNNs) maintain massive vital records in computer vision. While drawing attention worldwide, the design of the overall structure lacks general guidance. Based on the relationship between DNN design…

Computer Vision and Pattern Recognition · Computer Science 2021-07-29 Zhengbo Luo , Zitang Sun , Weilian Zhou , Zizhang Wu , Sei-ichiro Kamata

Neural networks often struggle with catastrophic forgetting when learning sequences of tasks or data streams, unlike humans who can continuously learn and consolidate new concepts even in the absence of explicit cues. Online…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Murat Onur Yildirim , Elif Ceren Gok Yildirim , Decebal Constantin Mocanu , Joaquin Vanschoren