Kolmogorov-Arnold Networks
PulseAugur coverage of Kolmogorov-Arnold Networks — every cluster mentioning Kolmogorov-Arnold Networks across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New theory bounds KAN training, reveals privacy-utility gap
Researchers have established new theoretical bounds for training Kolmogorov-Arnold Networks (KANs), a structured alternative to standard MLPs. The work analyzes KANs trained with mini-batch stochastic gradient descent (…
-
KAN-CL framework reduces catastrophic forgetting in continual learning
Researchers have introduced KAN-CL, a new framework for continual learning that addresses catastrophic forgetting by leveraging the unique structure of Kolmogorov-Arnold Networks (KANs). This method applies importance-w…
-
Bayesian KANs achieve near-minimax rates in new theory
Researchers have developed a theoretical framework for sparse Bayesian Kolmogorov-Arnold Networks (KANs). Their work establishes statistical foundations for KANs, demonstrating that these networks can achieve near-minim…
-
Neural Operators advance interpolation, resolution robustness, and Bayesian inference
Researchers are exploring new applications and improvements for neural operators, a class of models designed for learning maps between function spaces. One paper reframes neural operators as efficient function interpola…
-
Kolmogorov-Arnold Networks evolve with automated basis learning and practitioner's guide
Researchers have introduced InfinityKAN, a novel framework that automates the selection of basis functions in Kolmogorov-Arnold Networks (KANs), a theoretically grounded alternative to traditional multi-layer perceptron…
-
KANs gain temporal explanations with new Temporal Functional Circuits
Researchers have developed a new framework called Temporal Functional Circuits to enhance the interpretability of Kolmogorov-Arnold Networks (KANs) in time-series forecasting. This method transforms the KAN's internal e…
-
Quantum-inspired eigensolver slashes parameters, boosts performance for quantum chemistry
Researchers have developed a new quantum-inspired eigensolver called GQKAE, designed to improve the efficiency of high-performance computing in quantum chemistry. This model replaces traditional feed-forward networks wi…
-
P1-KAN network offers improved accuracy and convergence over MLPs
Researchers have introduced P1-KAN, a novel Kolmogorov-Arnold Network designed to approximate complex, irregular functions in high-dimensional spaces. The paper provides theoretical error bounds and universal approximat…
-
SRGAN-CKAN improves image super-resolution with efficient local operators
Researchers have developed SRGAN-CKAN, a novel framework for single-image super-resolution that enhances local operators for improved detail reconstruction. This approach integrates Convolutional Kolmogorov-Arnold Netwo…
-
KANs enable ultrafast on-chip online learning for low-latency systems
Researchers have demonstrated ultrafast online learning capabilities using Kolmogorov-Arnold Networks (KANs) on Field-Programmable Gate Arrays (FPGAs). This approach achieves sub-microsecond adaptation times, outperform…
-
New AI methods enhance time series forecasting accuracy and interpretability
Researchers have introduced several new methods for time-series forecasting, aiming to improve accuracy and generalization. MeLISA, a latent-free autoregressive model, enhances rollout efficiency and long-horizon statis…
-
New penalty method enhances KAN interpretability without sacrificing accuracy
Researchers have developed a new curvature penalty for Kolmogorov-Arnold Networks (KANs) to address issues with high-curvature oscillations in their activation functions. This penalty aims to improve the interpretabilit…
-
New research details Lipschitz-product control for deep KAN representations
Researchers have developed a method for deep Kolmogorov-Arnold Network (KAN) representations of complex functions, ensuring a layer-wise Lipschitz product control. This approach guarantees a domain-sensitive bound indep…
-
New research explores KAN universality and Gaussian-based network stability
Researchers have explored the universality of Kolmogorov-Arnold Networks (KANs), demonstrating that a single non-affine edge function, combined with affine ones, is sufficient for deep KANs to be universal approximators…
-
KANs for Time Series Forecasting reintroduce spectral bias with autocorrelation
A new paper reveals that Kolmogorov-Arnold Networks (KANs), previously thought to overcome spectral bias, actually reintroduce it when dealing with time series data due to temporal autocorrelation. Researchers found tha…
-
DecompKAN model offers transparent, accurate long-term time series forecasting
Researchers have introduced DecompKAN, a novel architecture for long-term time series forecasting that prioritizes both predictive accuracy and model interpretability. This lightweight, attention-free system integrates …
-
LTBs-KAN offers faster, more efficient Kolmogorov-Arnold Networks
Researchers have introduced LTBs-KAN, a novel variant of Kolmogorov-Arnold Networks (KANs) designed to overcome the significant speed limitations of their predecessors. This new architecture achieves linear time complex…