RylanSchaeffer / Stanford-AI-Alignment-Double-Descent-Tutorial
Code for Arxiv Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
☆24Updated last year
Alternatives and similar repositories for Stanford-AI-Alignment-Double-Descent-Tutorial:
Users that are interested in Stanford-AI-Alignment-Double-Descent-Tutorial are comparing it to the libraries listed below
- ☆26Updated last year
- Understanding how features learned by neural networks evolve throughout training☆32Updated 3 months ago
- ☆14Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆35Updated last year
- Portfolio REgret for Confidence SEquences☆14Updated last month
- Minimum Description Length probing for neural network representations☆18Updated this week
- Quantification of Uncertainty with Adversarial Models☆27Updated last year
- Official implementation of the paper "Interventions, Where and How? Experimental Design for Causal Models at Scale", NeurIPS 2022.☆19Updated 2 years ago
- Code for "Counterfactual Token Generation in Large Language Models", Arxiv 2024.☆23Updated 2 months ago
- Official code for the paper: "Metadata Archaeology"☆18Updated last year
- ☆28Updated last year
- ☆17Updated 2 years ago
- Repository for the PopulAtion Parameter Averaging (PAPA) paper☆26Updated 9 months ago
- Experiments for the NeurIPS 2021 paper "Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks"☆13Updated 3 years ago
- Automatic Integration for Neural Spatio-Temporal Point Process models (AI-STPP) is a new paradigm for exact, efficient, non-parametric inf…☆24Updated 3 months ago
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- Code for minimum-entropy coupling.☆31Updated 7 months ago
- ☆36Updated 2 years ago
- Official code for the paper "Compositional Generalization from First Principles" (NeurIPS 2023)☆9Updated last year
- Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"☆15Updated 2 years ago
- ☆15Updated 2 months ago
- 📰 Computing the information content of trained neural networks☆21Updated 3 years ago
- Google Research☆46Updated 2 years ago
- ☆24Updated 3 weeks ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆57Updated last year
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks"☆17Updated 3 weeks ago
- ☆48Updated 11 months ago
- ☆11Updated 8 months ago
- Evaluation of neuro-symbolic engines☆34Updated 5 months ago
- Official implementation of "Multi-scale Feature Learning Dynamics: Insights for Double Descent".☆16Updated 2 years ago