English
Related papers

Related papers: Lipschitz Constrained Parameter Initialization for…

200 papers

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

Deep Neural Networks have achieved remarkable success relying on the developing high computation capability of GPUs and large-scale datasets with increasing network depth and width in image recognition, object detection and many other…

Machine Learning · Computer Science 2020-01-08 E Zhenqian , Gao Weiguo

Transformers, especially the decoder-only variants, are the backbone of most modern large language models; yet we do not have much understanding of their expressive power except for the simple $1$-layer case. Due to the difficulty of…

Machine Learning · Computer Science 2024-12-05 Lijie Chen , Binghui Peng , Hongxun Wu

With the increasing implementation of machine learning models on edge or Internet-of-Things (IoT) devices, deploying advanced models on resource-constrained IoT devices remains challenging. Transformer models, a currently dominant neural…

Sound · Computer Science 2024-11-15 Zixing Zhang , Zhongren Dong , Weixiang Xu , Jing Han

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya

Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer…

Computation and Language · Computer Science 2024-12-17 Neha Verma , Maha Elbayad

We propose expanding the shared Transformer module to produce and initialize Transformers of varying depths, enabling adaptation to diverse resource constraints. Drawing an analogy to genetic expansibility, we term such module as learngene.…

Artificial Intelligence · Computer Science 2023-12-21 Shiyu Xia , Miaosen Zhang , Xu Yang , Ruiming Chen , Haokun Chen , Xin Geng

A class of mixed-order \emph{PDE}-constraint regularizer for image processing problem is proposed, generalizing the standard first order total variation $(TV)$. A semi-supervised (bilevel) training scheme, which provides a simultaneous…

Analysis of PDEs · Mathematics 2019-03-19 Pan Liu

In this work, we study data preconditioning, a well-known and long-existing technique, for boosting the convergence of first-order methods for regularized loss minimization. It is well understood that the condition number of the problem,…

Numerical Analysis · Computer Science 2015-09-28 Tianbao Yang , Rong Jin , Shenghuo Zhu , Qihang Lin

Deep denoisers have shown excellent performance in solving inverse problems in signal and image processing. In order to guarantee the convergence, the denoiser needs to satisfy some Lipschitz conditions like non-expansiveness. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-02-09 Deliang Wei , Peng Chen , Fang Li

The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with challenges such as…

Machine Learning · Computer Science 2026-02-25 Wei Wang , Xiao-Yong Wei , Qing Li

Though Transformers have achieved promising results in many computer vision tasks, they tend to be over-confident in predictions, as the standard Dot Product Self-Attention (DPSA) can barely preserve distance for the unbounded input domain.…

Machine Learning · Computer Science 2023-07-19 Wenqian Ye , Yunsheng Ma , Xu Cao , Kun Tang

Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network…

Computation and Language · Computer Science 2023-06-06 Wangchunshu Zhou , Ronan Le Bras , Yejin Choi

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the…

Computation and Language · Computer Science 2025-02-06 Andrea Santilli , Silvio Severino , Emilian Postolache , Valentino Maiorca , Michele Mancusi , Riccardo Marin , Emanuele Rodolà

In recent years, great progress has been made in a variety of application domains thanks to the development of increasingly deeper neural networks. Unfortunately, the huge number of units of these networks makes them expensive both…

Computer Vision and Pattern Recognition · Computer Science 2018-10-12 Jose M. Alvarez , Mathieu Salzmann

Recent advancement in next generation reconfigurable antenna and fluid antenna technology has influenced the wireless system with polarization reconfigurable (PR) channels to attract significant attention for promoting beneficial channel…

Signal Processing · Electrical Eng. & Systems 2025-08-19 Seungcheol Oh , Han Han , Joongheon Kim , Sean Kwon

Recently established equivalences between differential equations and the structure of neural networks enabled some interpretation of training of a neural network as partial-differential-equation (PDE) constrained optimization. We add to the…

Computer Vision and Pattern Recognition · Computer Science 2020-03-20 Bas Peters

In this effort we propose a novel approach for reconstructing multivariate functions from training data, by identifying both a suitable network architecture and an initialization using polynomial-based approximations. Training deep neural…

Machine Learning · Computer Science 2019-05-29 Joseph Daws , Clayton G. Webster

Decentralized optimization methods enable on-device training of machine learning models without a central coordinator. In many scenarios communication between devices is energy demanding and time consuming and forms the bottleneck of the…

Optimization and Control · Mathematics 2020-11-04 Dmitry Kovalev , Anastasia Koloskova , Martin Jaggi , Peter Richtarik , Sebastian U. Stich

We study a constrained training regime for decoder-only Transformers in which the token interface is fixed, previously trained dense blocks are not reopened, and the active trainable parameter set is kept approximately constant as depth…

Machine Learning · Computer Science 2026-05-05 A. Bochkov
‹ Prev 1 3 4 5 6 7 10 Next ›