The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size
☆19May 19, 2019Updated 7 years ago
Alternatives and similar repositories for DeepnetHessian
Users that are interested in DeepnetHessian are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆15Apr 27, 2019Updated 7 years ago
- Codebase for the paper "A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language"☆11Oct 11, 2024Updated 2 years ago
- can calculate the Hessian matrix and/or its spectrum for simple neural nets☆11May 7, 2018Updated 8 years ago
- Hessian spectral density estimation in TF and Jax☆125Sep 6, 2020Updated 6 years ago
- Working Group on Becoming Full-Stack AI Researchers (Fall 2025 - Fall 2026)☆11May 12, 2026Updated 6 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A code repository accompanying the paper "Transformers, parallel computation, and logarithmic depth" by Clayton Sanford, Daniel Hsu, and …☆12Feb 15, 2024Updated 2 years ago
- ☆15Sep 29, 2022Updated 4 years ago
- Official code for the paper Scale leads to compositional generalization.☆13Jul 11, 2025Updated last year
- ☆35Jul 5, 2023Updated 3 years ago
- ☆15Apr 19, 2020Updated 6 years ago
- Reproducing GPT on the TinyStories dataset☆22Jan 18, 2024Updated 2 years ago
- Regularization, Neural Network Training Dynamics☆14Jan 13, 2020Updated 6 years ago
- ☆32Feb 11, 2021Updated 5 years ago
- ☆85Jan 15, 2020Updated 6 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- 6,080-param transformer achieving 100% accuracy on 10-digit addition. Trained from scratch in 10 minutes.☆22Feb 19, 2026Updated 8 months ago
- ☆19Jun 10, 2024Updated 2 years ago
- Visualization of mean field and neural tangent kernel regime☆23Jul 25, 2024Updated 2 years ago
- Efficient PyTorch Hessian eigendecomposition tools!☆476Oct 23, 2026Updated 3 weeks ago
- You can easily generate mat files with different views from off file☆14Mar 6, 2019Updated 7 years ago
- Conformal Prediction + Federated Learning☆17Mar 16, 2024Updated 2 years ago
- A curated list of resources to help with computational research.☆21Jun 11, 2022Updated 4 years ago
- Official PyTorch code release for Implicit Gradient Transport, NeurIPS'19☆21Jun 11, 2019Updated 7 years ago
- ☆29Feb 20, 2026Updated 8 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Math tutor based on question asking☆13Jan 26, 2023Updated 3 years ago
- On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]☆36Jul 3, 2021Updated 5 years ago
- ☆21Nov 26, 2022Updated 3 years ago
- Large-batch Training, Neural Network Optimization☆11Nov 8, 2019Updated 7 years ago
- Torch implementation for Robust convolutional neural networks under adversarial noise☆13Mar 8, 2016Updated 10 years ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆30Oct 14, 2025Updated last year
- Likelihood Ratio Attack (LiRA) in PyTorch☆16Mar 3, 2025Updated last year
- Bias Mimicking: A simple sampling approach for Bias Mitigation (CVPR 23)☆14Aug 6, 2023Updated 3 years ago
- ICML 2020, Estimating Generalization under Distribution Shifts via Domain-Invariant Representations☆23Jun 30, 2020Updated 6 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)☆11Oct 31, 2024Updated 2 years ago
- ☆10Oct 3, 2024Updated 2 years ago
- Public Codebase for Rethinking Parameter Counting: Effective Dimensionality Revisited☆37Dec 27, 2022Updated 3 years ago
- Learning protein structure with a differentiable simulator☆27Jul 8, 2019Updated 7 years ago
- [ICML'21 Oral] Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding☆14Jun 10, 2021Updated 5 years ago
- ☆88Aug 31, 2023Updated 3 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆32Apr 25, 2022Updated 4 years ago
Are these results useful?