AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation Functions

Hong-Kun Zhang, Xin Li, Sikun Yang, Zhihong Jeff Xia

ICML 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Neural tangent kernel analysis

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Cauchy inversion activation instead of ReLU in a 128-unit single-hidden-layer networkCauchyNet · 1D rational-spike regressionMSE / peak fitImproved
CauchyNet versus SIREN, N-BEATS, FNNCauchyNet · Sharp-peak function approximationMAE: 3.2 -> 1.5Improved
CauchyNet versus baselines for forecastingCauchyNet · M4 subset trend forecastingMAE: 10+ -> 2.3Improved
CauchyNet versus baselines for gap fillingCauchyNet · 1D gap-filling imputationMSE and MAEImproved
add imaginary-part penalty to loss (ablation)CauchyNet · 1D sharp-peak functiontest MSEImproved
vary imaginary penalty lambda over 0.1 to 1.5 (ablation)CauchyNet · 1D sharp-peak functiontest MSEMixed
increase hidden size (ablation)CauchyNet · Parameter sensitivity heatmapstest MSEImproved
use learning rate 0.01 with weight decay 1e-5 (ablation)CauchyNet · Parameter sensitivity heatmapstest MSEImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy