{"total":37,"rows":[{"id":"2301.00557","title":"Learning to Maximize Mutual Information for Dynamic Feature Selection","created":"2023-01-02","cited_by_count":56,"area":null},{"id":"2106.06468","title":"Locally Sparse Neural Networks for Tabular Biomedical Data","created":"2021-06-11","cited_by_count":34,"area":null},{"id":"2102.13229","title":"Consistent Sparse Deep Learning: Theory and Computation","created":"2021-02-25","cited_by_count":27,"area":null},{"id":"2408.12025","title":"Exploring Large Language Models for Feature Selection: A Data-centric Perspective","created":"2024-08-21","cited_by_count":27,"area":null},{"id":"2401.08552","title":"Explaining Time Series via Contrastive and Locally Sparse Perturbations","created":"2024-01-16","cited_by_count":22,"area":null},{"id":"2306.03301","title":"Estimating Conditional Mutual Information for Dynamic Feature Selection","created":"2023-06-05","cited_by_count":21,"area":null},{"id":"2112.06580","title":"How to Find a Good Explanation for Clustering?","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2212.05427","title":"Statistical guarantees for sparse deep learning","created":"2022-12-11","cited_by_count":9,"area":null},{"id":"2110.00653","title":"Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration","created":"2021-10-01","cited_by_count":7,"area":null},{"id":"2207.02384","title":"Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data","created":"2022-07-06","cited_by_count":7,"area":null},{"id":"2211.06302","title":"GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2211.15616","title":"Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data","created":"2022-11-28","cited_by_count":6,"area":null},{"id":"2302.00878","title":"The Contextual Lasso: Sparse Linear Models via Deep Neural Networks","created":"2023-02-02","cited_by_count":6,"area":null},{"id":"2106.02260","title":"Regularization and Reparameterization Avoid Vanishing Gradients in Sigmoid-Type Networks","created":"2021-06-04","cited_by_count":5,"area":null},{"id":"2205.05428","title":"An Inexact Augmented Lagrangian Algorithm for Training Leaky ReLU Neural Network with Group Sparsity","created":"2022-05-11","cited_by_count":5,"area":null},{"id":"2503.09494","title":"Representation Retrieval Learning for Heterogeneous Data Integration","created":"2025-03-12","cited_by_count":5,"area":null},{"id":"2204.07293","title":"Towards a Unified Framework for Uncertainty-aware Nonlinear Variable Selection with Theoretical Guarantees","created":"2022-04-15","cited_by_count":4,"area":null},{"id":"2211.05499","title":"DisPositioNet: Disentangled Pose and Identity in Semantic Image Manipulation","created":"2022-11-10","cited_by_count":4,"area":null},{"id":"2307.00344","title":"Sparse-Input Neural Network using Group Concave Regularization","created":"2023-07-01","cited_by_count":4,"area":null},{"id":"2308.16637","title":"Learning Channel Importance for High Content Imaging with Interpretable Deep Input Channel Mixing","created":"2023-08-31","cited_by_count":3,"area":null},{"id":"2310.18531","title":"Feature Selection in the Contrastive Analysis Setting","created":"2023-10-27","cited_by_count":3,"area":null},{"id":"2201.08652","title":"A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks","created":"2022-01-21","cited_by_count":2,"area":null},{"id":"2107.07160","title":"Lockout: Sparse Regularization of Neural Networks","created":"2021-07-15","cited_by_count":1,"area":null},{"id":"2109.13061","title":"Searching for Minimal Optimal Neural Networks","created":"2021-09-27","cited_by_count":1,"area":null},{"id":"2304.03202","title":"SLM: End-to-end Feature Selection via Sparse Learnable Masks","created":"2023-04-06","cited_by_count":1,"area":null},{"id":"2308.03704","title":"DeRisk: An Effective Deep Learning Framework for Credit Risk Prediction over Real-World Financial Data","created":"2023-08-07","cited_by_count":1,"area":null},{"id":"2402.16661","title":"Penalized Generative Variable Selection","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2511.07997","title":"PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2106.02197","title":"Top-$k$ Regularization for Supervised Feature Selection","created":"2021-06-04","cited_by_count":0,"area":null},{"id":"2207.04969","title":"From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process","created":"2022-07-11","cited_by_count":0,"area":null},{"id":"2209.07011","title":"Error Controlled Feature Selection for Ultrahigh Dimensional and Highly Correlated Feature Space Using Deep Learning","created":"2022-09-15","cited_by_count":0,"area":null},{"id":"2211.15081","title":"Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2310.18542","title":"End-to-end Feature Selection Approach for Learning Skinny Trees","created":"2023-10-28","cited_by_count":0,"area":null},{"id":"2405.02534","title":"A Multi-Domain Multi-Task Approach for Feature Selection from Bulk RNA Datasets","created":"2024-05-04","cited_by_count":0,"area":null},{"id":"2406.18137","title":"Sparse deep neural networks for nonparametric estimation in high-dimensional sparse regression","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2607.00995","title":"Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.38263","title":"Robust LassoNet: Enhancing Feature Selection in Neural Networks via Robust Loss Functions","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}