3 papers
cs.LG2026
Stochastic Adaptive Fourier Decomposition for Operator Learning
Pengqing Shi, Liming Zhang, Tao Qian +3
Fourier Neural Operators (FNOs) offer an efficient paradigm for solving partial differential equations (PDEs). However, FNOs rely on a fixed Fourier basis and hard frequency trunca…
cs.LG2026
SirenFNO: Efficient and Full Frequency Learning of Fourier Neural Operators
Pengqing Shi, Jie Yin, Stephen Tierney +1
Fourier neural operators (FNOs) are effective and efficient surrogates for approximating solutions of PDEs and generalize across discretizations. However, owing to the reliance on…
stat.ME2026
CAIRO: Decoupling Order from Scale in Regression
Harri Vanhems, Yue Zhao, Peng Shi +1
Standard regression methods typically optimize a single pointwise objective, such as mean squared error, which conflates the learning of ordering with the learning of scale. This c…