English
Related papers

Related papers: Sprecher Networks: A Parameter-Efficient Kolmogoro…

200 papers

Kolmogorov-Arnold Networks (KANs) offer a structured and interpretable framework for multivariate function approximation by composing univariate transformations through additive or multiplicative aggregation. This paper establishes…

Machine Learning · Computer Science 2025-12-05 Wei Liu , Eleni Chatzi , Zhilu Lai

Symbolic discovery of governing equations is a long-standing goal in scientific machine learning, yet a fundamental trade-off persists between interpretability and scalable learning. Classical symbolic regression methods yield explicit…

Machine Learning · Computer Science 2026-03-26 Salah A Faroughi , Farinaz Mostajeran , Amirhossein Arzani , Shirko Faroughi

For many real-world applications, understanding feature-outcome relationships is as crucial as achieving high predictive accuracy. While traditional neural networks excel at prediction, their black-box nature obscures underlying functional…

Machine Learning · Computer Science 2025-10-03 Wangxuan Fan , Ching Wang , Siqi Li , Nan Liu

In this paper, we exploit the concept of Kolmogorov $n$-widths to establish optimality benchmarks for reduced-order methods used in phononic, acoustic, and photonic band structure calculations. The Bloch-transformed operators are entire…

Numerical Analysis · Mathematics 2026-04-07 Ankit Srivastava

Kolmogorov-Arnold Networks (KANs) shift neural computation from linear layers to learnable nonlinear edge functions, but implementing these nonlinearities efficiently in hardware remains an open challenge. Here we introduce a physical…

We introduce Graph Kolmogorov-Arnold Networks (GKAN), an innovative neural network architecture that extends the principles of the recently proposed Kolmogorov-Arnold Networks (KAN) to graph-structured data. By adopting the unique…

Machine Learning · Computer Science 2024-06-11 Mehrdad Kiamari , Mohammad Kiamari , Bhaskar Krishnamachari

Over the last two decades, language modeling has experienced a shift from the use of predominantly recurrent architectures that process tokens sequentially during training and inference to non-recurrent models that process sequence elements…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters…

Computation and Language · Computer Science 2025-01-31 Mohamed Elfeki , Rui Liu , Chad Voegele

Neural networks are fundamental tools of modern machine learning. The standard paradigm assumes binary interactions (across feedforward linear passes) between inter-tangled units, organized in sequential layers. Generalized architectures…

Machine Learning · Computer Science 2026-03-31 Gianluca Peri , Timoteo Carletti , Duccio Fanelli , Diego Febbe

Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical expressiveness, they suffer from severe parameter explosion and limited ability to capture high-frequency features in high-dimensional tasks. To…

Machine Learning · Computer Science 2026-05-26 Jusheng Zhang , Yijia Fan , Kaitong Cai , Keze Wang , Wenhao Wang

Network slicing is a key technology enabling the flexibility and efficiency of 5G networks, offering customized services for diverse applications. However, existing methods face challenges in adapting to dynamic network environments and…

Networking and Internet Architecture · Computer Science 2025-02-25 Ming Zhao , Yuru Zhang , Qiang Liu , Ahan Kak , Nakjung Choi

We introduce a parameter sharing scheme, in which different layers of a convolutional neural network (CNN) are defined by a learned linear combination of parameter tensors from a global bank of templates. Restricting the number of templates…

Machine Learning · Computer Science 2019-03-15 Pedro Savarese , Michael Maire

Kolmogorov-Arnold Networks (KANs) replace scalar weights with per-edge vectors of basis coefficients, thereby increasing expressivity and accuracy while also resulting in a multiplicative increase in parameters and memory. We propose…

Machine Learning · Computer Science 2026-02-10 Matthew Raffel , Adwaith Renjith , Lizhong Chen

We introduce and train distributed neural architectures (DNA) in vision and language domains. DNAs are initialized with a proto-architecture that consists of (transformer, MLP, attention, etc.) modules and routers. Any token (or patch) can…

Machine Learning · Computer Science 2025-06-30 Aditya Cowsik , Tianyu He , Andrey Gromov

Deep neural networks (DNNs) and Kolmogorov-Arnold networks (KANs) are popular methods for function approximation due to their flexibility and expressivity. However, they typically require a large number of trainable parameters to produce a…

Machine Learning · Computer Science 2025-11-27 Zachary Morrow , Michael Penwarden , Brian Chen , Aurya Javeed , Akil Narayan , John D. Jakeman

Recent progress in speech separation has been largely driven by advances in deep neural networks, yet their high computational and memory requirements hinder deployment on resource-constrained devices. A significant inefficiency in…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-09 Mohamed Elminshawi , Srikanth Raj Chetupalli , Emanuël A. P. Habets

Tensorial neural networks (TNNs) combine the successes of multilinear algebra with those of deep learning to enable extremely efficient reduced-order models of high-dimensional problems. Here, I describe a deep neural network architecture…

Machine Learning · Computer Science 2023-12-27 Caleb G. Wagner

The highly nonlinear degradation process, complex physical interactions, and various sources of uncertainty render single-image Super-resolution (SR) a particularly challenging task. Existing interpretable SR approaches, whether based on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Chenyu Li , Danfeng Hong , Bing Zhang , Zhaojie Pan , Jocelyn Chanussot

Currently, most speaker recognition backends, such as cosine, linear discriminant analysis (LDA), or probabilistic linear discriminant analysis (PLDA), make decisions by calculating similarity or distance between enrollment and test…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-21 Liang He , Ruida Li , Mengqi Niu

We propose a novel variant of SGD customized for training network architectures that support anytime behavior: such networks produce a series of increasingly accurate outputs over time. Efficient architectural designs for these networks…

Machine Learning · Computer Science 2020-08-18 Chengcheng Wan , Henry Hoffmann , Shan Lu , Michael Maire