# GRIP2: A Robust and Powerful Deep Knockoff Method for Feature Selection

arXiv: https://arxiv.org/abs/2602.00218 · HTML: https://mlsanity.com/paper/2602.00218/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 12 of 12)

- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Panning for Gold: Model-X Knockoffs for High-dimensional Controlled Variable Selection](https://mlsanity.com/paper/1610.02351/) (2016)
- [Controlling the false discovery rate via knockoffs](https://mlsanity.com/paper/1404.5609/) (2014)
- [DeepPINK: reproducible feature selection in deep neural networks](https://mlsanity.com/paper/1809.01185/) (2018)
- [Derandomized knockoffs: leveraging e-values for false discovery rate control](https://mlsanity.com/paper/2205.15461/) (2022)
- [Derandomizing Knockoffs](https://mlsanity.com/paper/2012.02717/) (2020)
- [Improving the Stability of the Knockoff Procedure: Multiple Simultaneous Knockoffs and Entropy Maximization](https://mlsanity.com/paper/1810.11378/) (2018)
- [Deep neural networks with controlled variable selection for the identification of putative causal genetic variants](https://mlsanity.com/paper/2109.14719/) (2021)
- [Deep-gKnock: nonlinear group-feature selection with deep neural network](https://mlsanity.com/paper/1905.10013/) (2019)
- [Novel Knockoff Generation and Importance Measures with Heterogeneous Data via Conditional Residuals and Local Gradients](https://mlsanity.com/paper/2508.14882/) (2025)

## Abstract (arXiv)

Identifying truly predictive covariates while strictly controlling false discoveries remains a fundamental challenge in nonlinear, highly correlated, and low signal-to-noise regimes, where deep learning based feature selection methods are most attractive. We propose Group Regularization Importance Persistence in 2 Dimensions (GRIP2), a deep knockoff feature importance statistic that integrates first-layer feature activity over a two-dimensional regularization surface controlling both sparsity strength and sparsification geometry. To approximate this surface integral in a single training run, we introduce efficient block-stochastic sampling, which aggregates feature activity magnitudes across diverse regularization regimes along the optimization trajectory. The resulting statistics are antisymmetric by construction, ensuring finite-sample FDR control. In extensive experiments on synthetic and semi-real data, GRIP2 demonstrates improved robustness to feature correlation and noise level: in high correlation and low signal-to-noise ratio regimes where standard deep learning based feature selectors may struggle, our method retains high power and stability. Finally, on real-world HIV drug resistance data, GRIP2 recovers known resistance-associated mutations with power better than established linear baselines, confirming its reliability in practice.