Statistical Gains from Looped Estimation under Parameter Budgets
stat.ML, cs.LG, math.ST, stat.TH
Submitted: 2026-09-22
Updated: 2026-09-27
Comments: 57 pages, 5 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Recurrent neural networks approximate continuous functions
- Universal Transformers
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- Approximation Bounds for Recurrent Neural Networks with Application to Regression
- Deep Network Approximation for Smooth Functions
- Loop Neural Networks for Parameter Sharing
- Nonparametric regression using deep neural networks with ReLU activation function
- How to Train Your Energy-Based Models
- Looped Transformers are Better at Learning Learning Algorithms
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
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey