PyTorch library TorchCurves introduces learnable parametric curves

A new PyTorch library called TorchCurves has been introduced, enabling the use of vector-valued parametric curves as learnable components within machine learning models. This library allows for the optimization of curve coefficients alongside other model parameters or through a separate network. TorchCurves supports various applications, including continuous feature embeddings, Kolmogorov-Arnold networks, and functional regression, by offering trainable modules and a functional interface. Performance benchmarks indicate that while the library is generally efficient, its computational overhead can become substantial for larger problem sizes. AI

IMPACT Enables new modeling approaches for continuous data and functional regression within PyTorch.

RANK_REASON The cluster describes a new library for machine learning research published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• B-spline
• EfficientKAN
• GitHub
• Hugging Face
• Kolmogorov-Arnold Networks
• Legendre polynomial
• NumPy
• PyTorch
• SciPy
• TorchCurves

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →