English
Related papers

Related papers: Lipschitz Constrained Parameter Initialization for…

200 papers

Despite the remarkable success of deep learning in pattern recognition, deep network models face the problem of training a large number of parameters. In this paper, we propose and evaluate a novel multi-path wavelet neural network…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 D. D. N. De Silva , H. W. M. K. Vithanage , K. S. D. Fernando , I. T. S. Piyatilake

Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood. In encoder-decoder arithmetic models, we…

Machine Learning · Computer Science 2026-04-16 Laura Gomezjurado Gonzalez

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…

Computation and Language · Computer Science 2023-05-12 Yanyang Li , Ye Lin , Tong Xiao , Jingbo Zhu

Transformers, the standard implementation for large language models (LLMs), typically consist of tens to hundreds of discrete layers. While more layers can lead to better performance, this approach has been challenged as far from efficient,…

Machine Learning · Computer Science 2025-05-21 Yen-Chen Wu , Feng-Ting Liao , Meng-Hsi Chen , Pei-Chen Ho , Farhang Nabiei , Da-shan Shiu

Many different deep networks have been used to approximate, accelerate or improve traditional image operators, such as image smoothing, super-resolution and denoising. Among these traditional operators, many contain parameters which need to…

Computer Vision and Pattern Recognition · Computer Science 2018-08-10 Qingnan Fan , Dongdong Chen , Lu Yuan , Gang Hua , Nenghai Yu , Baoquan Chen

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

Deep learning models generalize well to in-distribution data but struggle to generalize compositionally, i.e., to combine a set of learned primitives to solve more complex tasks. In sequence-to-sequence (seq2seq) learning, transformers are…

Machine Learning · Computer Science 2021-12-13 Luana Ruiz , Joshua Ainslie , Santiago Ontañón

Deep learning models named transformers achieved state-of-the-art results in a vast majority of NLP tasks at the cost of increased computational complexity and high memory consumption. Using the transformer model in real-time inference…

Given an existing trained neural network, it is often desirable to learn new capabilities without hindering performance of those already learned. Existing approaches either learn sub-optimal solutions, require joint training, or incur a…

Computer Vision and Pattern Recognition · Computer Science 2018-02-15 Amir Rosenfeld , John K. Tsotsos

Deep Neural Networks have achieved remarkable success relying on the developing availability of GPUs and large-scale datasets with increasing network depth and width. However, due to the expensive computation and intensive memory,…

Machine Learning · Computer Science 2020-09-07 E Zhenqian , Gao Weiguo

Overparameterization refers to the important phenomenon where the width of a neural network is chosen such that learning algorithms can provably attain zero loss in nonconvex training. The existing theory establishes such global convergence…

Machine Learning · Computer Science 2021-11-04 Chaehwan Song , Ali Ramezani-Kebrya , Thomas Pethick , Armin Eftekhari , Volkan Cevher

Mesh denoising, aimed at removing noise from input meshes while preserving their feature structures, is a practical yet challenging task. Despite the remarkable progress in learning-based mesh denoising methodologies in recent years, their…

Computer Vision and Pattern Recognition · Computer Science 2024-05-13 Wenbo Zhao , Xianming Liu , Deming Zhai , Junjun Jiang , Xiangyang Ji

Regularization is a critical component in deep learning. The most commonly used approach, weight decay, applies a constant penalty coefficient uniformly across all parameters. This may be overly restrictive for some parameters, while…

Machine Learning · Computer Science 2024-12-10 Jörg K. H. Franke , Michael Hefenbrock , Gregor Koehler , Frank Hutter

While the transformer architecture has achieved state-of-the-art performance on natural language processing tasks, these models impose substantial memory and computational overhead. Recent research has identified significant architectural…

Computation and Language · Computer Science 2026-04-01 Shivanshu Kumar , Gopalakrishnan Srinivasan

Tensor decomposition methods allow us to learn the parameters of latent variable models through decomposition of low-order moments of data. A significant limitation of these algorithms is that there exists no general method to regularize…

Machine Learning · Statistics 2019-05-28 Omer Gottesman , Weiwei Pan , Finale Doshi-Velez

Deep residual networks (ResNets) have demonstrated outstanding success in computer vision tasks, attributed to their ability to maintain gradient flow through deep architectures. Simultaneously, controlling the Lipschitz constant in neural…

Machine Learning · Computer Science 2025-12-08 Marius F. R. Juston , Ramavarapu S. Sreenivas , Dustin Nottage , Ahmet Soylemezoglu

Deep networks often suffer from vanishing or exploding gradients due to inefficient signal propagation, leading to long training times or convergence difficulties. Various architecture designs, sophisticated residual-style networks, and…

To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, the nonlinear and compositional structure of these models…

Machine Learning · Computer Science 2021-12-21 Karl Hajjar , Lénaïc Chizat , Christophe Giraud

This paper studies the problem of linear precoding for multiple-input multiple-output (MIMO) communication channels employing finite-alphabet signaling. Existing solutions typically suffer from high computational complexity due to costly…

Information Theory · Computer Science 2021-11-08 Maksym A. Girnyk

Transformer models have established new benchmarks in natural language processing; however, their increasing depth results in substantial growth in parameter counts. While existing recurrent transformer methods address this issue by…

Computation and Language · Computer Science 2025-05-27 Anthony Nguyen , Wenjun Lin