Research map / Probabilistic and scientific modeling / Molecules and proteins
From Bayesian Sparsity to Gated Recurrent Nets
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use the gated-feedback recurrent network instead of SBL | Sparse recovery with correlated dictionaries · DOA estimation across SNR values | Chamfer distance | Helped |
| Use the gated-feedback recurrent network instead of SBL | Photometric stereo · Bunny, r=10 | Average angular error (degrees): 4.02 -> 1.35 | Helped |
| Use the gated-feedback recurrent network instead of MaxSparseNet | Photometric stereo · Bunny, r=40 | Average angular error (degrees): 1.20 -> 1.12 | Hurt |
| Use the gated-feedback recurrent network instead of SBL | Photometric stereo · Caesar, r=40 | Average angular error (degrees): 0.34 -> 0.60 | Hurt |
| Use the gated-feedback recurrent network instead of SBL | Photometric stereo · Bunny, r=10 | Runtime (sec.): 35.46 -> 0.63 | Helped |
| Add gated feedback between recurrent layers (ablation) | Gated recurrent sparse recovery network · Synthetic correlated dictionaries, d/n = 0.4 | Strict accuracy | Helped |
| Increase the recurrent network size (ablation) | Gated recurrent sparse recovery network · Synthetic correlated dictionaries, d/n = 0.4 | Strict accuracy | Helped |
| Use LSTM cells instead of GRU cells (ablation) | Gated recurrent sparse recovery network · Synthetic correlated dictionaries, d/n = 0.4 | Strict accuracy | No clear effect |
| Use the learned network instead of SBL | Sparse recovery with correlated dictionaries · Synthetic correlated dictionaries | Loose accuracy | Helped |
Closest papers by meaning
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.88)
- Sparse maximal update parameterization: A holistic approach to sparse training dynamics (NeurIPS 2024 · similarity 0.88)
- Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks (ICLR 2024 · similarity 0.88)
- Training Bayesian Neural Networks with Sparse Subspace Variational Inference (ICLR 2024 · similarity 0.88)
- Effective Interplay between Sparsity and Quantization: From Theory to Practice (ICLR 2025 · similarity 0.87)
- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs (ICLR 2024 · similarity 0.87)
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.