English
Related papers

Related papers: Training Transformers in Cosine Coefficient Space

200 papers

Typical convolutional networks are trained and conducted on RGB images. However, images are often compressed for memory savings and efficient transmission in real-world applications. In this paper, we explore methods for performing semantic…

Computer Vision and Pattern Recognition · Computer Science 2020-01-01 Shao-Yuan Lo , Hsueh-Ming Hang

Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require millions of parameters for good accuracy performance. With increasing applications…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Yuhuang Hu , Shih-Chii Liu

Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e.g., image classification, natural language processing, etc. Despite the good performance, the huge number of parameters in DNNs brings…

Machine Learning · Computer Science 2020-12-21 Jinmian Ye , Guangxi Li , Di Chen , Haiqin Yang , Shandian Zhe , Zenglin Xu

We propose computationally efficient encoders and decoders for lossy compression using a Sparse Regression Code. The codebook is defined by a design matrix and codewords are structured linear combinations of columns of this matrix. The…

Information Theory · Computer Science 2014-05-20 Ramji Venkataramanan , Tuhin Sarkar , Sekhar Tatikonda

An orthogonal approximation for the 8-point discrete cosine transform (DCT) is introduced. The proposed transformation matrix contains only zeros and ones; multiplications and bit-shift operations are absent. Close spectral behavior…

Multimedia · Computer Science 2014-02-26 R. J. Cintra , F. M. Bayer

Trainable layers such as convolutional building blocks are the standard network design choices by learning parameters to capture the global context through successive spatial operations. When designing an efficient network, trainable layers…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Dongyoon Han , YoungJoon Yoo , Beomyoung Kim , Byeongho Heo

We demonstrate that 1x1-convolutions in 1D time-channel separable convolutions may be replaced by constant, sparse random ternary matrices with weights in $\{-1,0,+1\}$. Such layers do not perform any multiplications and do not require…

Machine Learning · Computer Science 2021-10-22 Gonçalo Mordido , Matthijs Van Keirsbilck , Alexander Keller

Parameter-Efficient Fine-Tuning (PEFT) of text-to-image models has become an increasingly popular technique with many applications. Among the various PEFT methods, Low-Rank Adaptation (LoRA) and its variants have gained significant…

Machine Learning · Computer Science 2025-08-01 Zerui Tao , Yuhta Takida , Naoki Murata , Qibin Zhao , Yuki Mitsufuji

This paper studies the cosine as basis function for the approximation of univariate and continuous functions without memory. This work studies a supervised learning to obtain the approximation coefficients, instead of using the Discrete…

Signal Processing · Electrical Eng. & Systems 2024-05-28 Ana I. Pérez-Neira , Marc Martinez-Gost , Miguel Ángel Lagunas

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…

Machine Learning · Computer Science 2026-05-05 Arian Eamaz , Farhang Yeganegi , Mojtaba Soltanalian

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

The ability to learn robust policies while generalizing over large discrete action spaces is an open challenge for intelligent systems, especially in noisy environments that face the curse of dimensionality. In this paper, we present a…

Machine Learning · Computer Science 2023-06-29 Pranavi Pathakota , Hardik Meisheri , Harshad Khadilkar

Deep learning using neural networks is an effective technique for generating models of complex data. However, training such models can be expensive when networks have large model capacity resulting from a large number of layers and nodes.…

Machine Learning · Computer Science 2023-01-19 Jarom D. Hogue , Robert M. Kirby , Akil Narayan

Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened…

Computer Vision and Pattern Recognition · Computer Science 2016-08-10 Ke Yu , Chao Dong , Chen Change Loy , Xiaoou Tang

Representation learning for the electronic structure problem is a major challenge of machine learning in computational condensed matter and materials physics. Within quantum mechanical first principles approaches, Kohn-Sham density…

Materials Science · Physics 2024-04-24 Bowen Hou , Jinyuan Wu , Diana Y. Qiu

DeepTensor is a computationally efficient framework for low-rank decomposition of matrices and tensors using deep generative networks. We decompose a tensor as the product of low-rank tensor factors (e.g., a matrix as the outer product of…

Large language models (LLMs) show excellent performance in difficult tasks, but they often require massive memories and computational resources. How to reduce the parameter scale of LLMs has become research hotspots. In this study, we make…

Machine Learning · Computer Science 2024-04-16 Guangyan Li , Yongqiang Tang , Wensheng Zhang

It was conjectured that any neural network of any structure and arbitrary differentiable transfer functions at the nodes cannot learn the following problem sample efficiently when trained with gradient descent: The instances are the rows of…

Machine Learning · Computer Science 2020-10-20 Manfred K. Warmuth , Wojciech Kotłowski , Ehsan Amid

Model compression techniques, such as pruning and quantization, are becoming increasingly important to reduce the memory footprints and the amount of computations. Despite model size reduction, achieving performance enhancement on devices…

Machine Learning · Computer Science 2020-03-06 Se Jung Kwon , Dongsoo Lee , Byeongwook Kim , Parichay Kapoor , Baeseong Park , Gu-Yeon Wei

Transformers can acquire Chain-of-Thought (CoT) capabilities to solve complex reasoning tasks through fine-tuning. Reinforcement learning (RL) and supervised fine-tuning (SFT) are two primary approaches to this end. In this work, we…

Machine Learning · Computer Science 2026-05-27 Bochen Lyu , Yiyang Jia , Xiaohao Cai , Zhanxing Zhu