Variable Importance Identification Through Lazy Training for Binary Classification

arXiv:2607.22979 · stat.ML, cs.LG · Submitted 2026-07-25 · Read on arXiv

Anand Singh, Luke Pennella, Eshan Kabir, Xiaoxi Shen

stat.ML, cs.LG

Submitted: 2026-07-25

Code: https://github.com/SxxMichael/DNN-LazyVI-Binary-Classification

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Variable Importance — 26× in this paper
• Fixed Point — 17× in this paper · explained in 2 episodes
• ReLU Network — 11× in this paper · explained in 2 episodes
• Loss Function — 7× in this paper · explained in 2 episodes
• Generalization — 6× in this paper · explained in 14 episodes
• Hilbert Space — 6× in this paper · explained in 2 episodes
• Regularization — 6× in this paper · explained in 3 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Explainability — 5× in this paper · explained in 4 episodes
• Feature Importance — 5× in this paper · explained in 2 episodes
• Overfitting — 3× in this paper · explained in 2 episodes
• Hyperparameters — 2× in this paper · explained in 2 episodes
• Model-Agnostic — 2× in this paper · explained in 2 episodes
• Reproducing Kernel Hilbert Space (RKHS) — 2× in this paper · explained in 7 episodes
• Sample Complexity — 2× in this paper · explained in 20 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Artificial Intelligence (AI) — 1× in this paper · explained in 2 episodes
• Asymptotic Normality — 1× in this paper · explained in 2 episodes
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Computational Efficiency — 1× in this paper · explained in 2 episodes
• Convergence Guarantees — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Inductive Bias — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Mechanistic Interpretability — 1× in this paper · explained in 4 episodes
• Modified National Institute of Standards and Technology — 1× in this paper
• Neural Tangent Kernel (NTK) — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Transformers — 1× in this paper · explained in 2 episodes

Sources

• Deep Equals Shallow for ReLU Networks in Kernel Regimes
• Gradient Descent Provably Optimizes Over-parameterized Neural Networks
• RISE: Randomized Input Sampling for Explanation of Black-box Models
• A Sieve Quasi-likelihood Ratio Test for Neural Networks with Applications to Genetic Association Studies
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• SmoothGrad: removing noise by adding noise
• Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Scalable Posterior Uncertainty for Flexible Density-Based Clustering
• A Transport Geometry of Benign Overfitting
• Efficient quadratic entropy with distance sketches