AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

LassoFlexNet: a Flexible Neural Architecture for Tabular Data

Kry Yik-Chau Lui, Cheng Chi, Kishore Basu, Yanshuai Cao

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Layer-wise analysis of language models

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
add EMA to Seq-Hier-Prox (ablation)LassoFlexNet · California Housingtest RMSE: 0.4195 -> 0.4047Improved
replace LassoNet Hier-Prox with sequential Seq-Hier-Prox (ablation)LassoFlexNet · California Housingtest RMSE: 0.4320 -> 0.4047Improved
add proximal gradient (vs Adam without proximal) (ablation)LassoFlexNet · California Housingtest RMSE: 0.4272 -> 0.4047Improved
add piecewise linear encoding (PLE) (ablation)LassoFlexNet · California Housingtest RMSE: 0.4387 -> 0.4047Improved
add per-feature embeddings (PFE) (ablation)LassoFlexNet · California Housingtest RMSE: 0.5371 -> 0.4047Improved
use nonlinear instead of linear PFE layers (ablation)LassoFlexNet · California Housingtest RMSE: 0.4145 -> 0.4047Improved
use parameter-free BatchNorm instead of learnable BatchNorm (ablation)LassoFlexNet · California Housingtest RMSE: 0.4191 -> 0.4047Improved
use MLP-Mixer instead of a plain MLP backbone (ablation)LassoFlexNet · California Housingtest RMSE: 0.8453 -> 0.4047 (MLP 1); 0.8406 -> 0.4047 (MLP 2)Improved
add linear skip connection to the Mixer (ablation)LassoFlexNet · California Housingtest RMSE: 0.4221 -> 0.4047Improved
use tau < 1 soft curriculum (vs tau = 1) (ablation)LassoFlexNet · California Housingtest RMSE: 0.4047 -> 0.4004 (tau = 1)No clear effect
add PLE to linear LassoNet (ablation)Linear LassoNet · California Housingtest RMSE: 0.5263 -> 0.5226No clear effect
switch LassoNet optimizer to Adam or Adam with HGD (ablation)Linear LassoNet · California Housingtest RMSE: 0.5263 -> 0.5291 (Adam), 0.5294 (AdamHGD)No clear effect

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