PyTorchKR Papers

최신 논문

총 2편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2607.11110v1cs.LG

Neural Discovery of Memory and Nonlocal Kernels in Integro-Differential Equations with Constrained Kolmogorov--Arnold Networks

Discovering the memory or nonlocal kernel governing an integro-differential equation (IDE) from sparse and noisy observations is an ill-posed inverse problem. Existing identification methods often rely on problem-specific analytical derivations, specialized observation requirements, or restrictive assumptions about the kernel, limiting their applicability across different classes of IDEs. In this work, we propose a differentiable-solver-based framework for discovering memory and nonlocal kernels directly from spatiotemporal observations. Within the solver, the unknown kernel is represented using a constrained Kolmogorov--Arnold Network (KAN) parameterization, with the physical constraints imposed through two different approaches: a Bernstein-polynomial-based Monotone--Convex KAN (MC-KAN), whose coefficient constraints enforce positivity, monotonic decrease, and convexity by construction, and a Chebyshev-based KAN (Cheb-KAN), in which the same properties are encouraged through soft penalty terms. After training, symbolic regression is applied to the learned kernels to obtain interpretable closed-form representations. We evaluate both methods on benchmarks spanning a one-dimensional Volterra equation, a one-dimensional viscoelastic wave partial integro-differential equation, and a two-dimensional nonlocal reaction-diffusion equation with an anisotropic coupled kernel. For the 1D problems, both methods recover the correct kernel functional form and achieve comparable solution-reconstruction accuracy. In contrast, for the sparse and noisy 2D nonlocal problem, the hard-constrained MC-KAN consistently achieves lower kernel reconstruction errors than the soft-constrained Cheb-KAN. Our results demonstrate that enforcing physically motivated shape constraints by construction provides greater robustness than soft penalties for multidimensional kernel discovery from sparse and noisy observations.

arXiv:2411.09734v3cs.LG공식 코드 · Papers with Code

적분-미분 방정식으로 AdaGrad, RMSProp, Adam 모델링

Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations

본 논문에서는 AdaGrad, RMSProp, Adam 최적화 알고리즘을 1차 적분-미분 방정식으로 모델링하여 연속 시간 공식을 제안한다. 이 방정식들에 대해 수치 시뮬레이션을 수행하고, 안정성 및 수렴(convergence) 분석을 통해 원본 알고리즘의 정확한 근사로서의 유효성을 입증한다. 실험 결과, 연속 시간 모델의 동작과 이산 구현 간의 높은 일치도를 확인하였으며, 이를 통해 적응형 최적화 방법의 이론적 이해에 새로운 관점을 제시한다.