Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithms

arXiv:2505.15661 · cs.LG, cs.NA, cs.NE, math.NA · Submitted 2025-05-21 · Read on arXiv

cs.LG, cs.NA, cs.NE, math.NA

Submitted: 2025-05-21

Updated: 2026-08-26

Code: https://github.com/sina-taheri/Deep

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

Terminology

• Sparsity — 19× in this paper · explained in 4 episodes
• Accuracy — 14× in this paper · explained in 1 episode
• Orthogonal Matching Pursuit — 9× in this paper
• Iterative Hard Thresholding — 6× in this paper
• Interpretability — 4× in this paper · explained in 15 episodes
• Artificial Intelligence — 3× in this paper
• Core — 3× in this paper · explained in 2 episodes
• Gradient Flow — 3× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Optimal Transport — 2× in this paper · explained in 5 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Artificial Intelligence (AI) — 1× in this paper · explained in 2 episodes
• Convergence Guarantees — 1× in this paper · explained in 3 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Inverse Problem — 1× in this paper · explained in 2 episodes
• Iterative Shrinkage-Thresholding Algorithm — 1× in this paper
• Sample Complexity — 1× in this paper · explained in 15 episodes

Sources

• Multi-level Compressed Sensing Petrov-Galerkin discretization of high-dimensional parametric PDEs
• On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning
• Stochastic Optimization of Sorting Networks via Continuous Relaxations
• Categorical Reparameterization with Gumbel-Softmax
• Iterative Hard Thresholding for Weighted Sparse Approximation
• Learning Latent Permutations with Gumbel-Sinkhorn Networks

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks