leopard-ai / betty
Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization
☆330Updated 2 months ago
Related projects: ⓘ
- Framework code with wandb, checkpointing, logging, configs, experimental protocols. Useful for fine-tuning models or training from scratc…☆146Updated last year
- A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...☆242Updated 3 weeks ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆555Updated 4 months ago
- ☆290Updated 2 months ago
- Cockpit: A Practical Debugging Tool for Training Deep Neural Networks☆474Updated 2 years ago
- Implementation of https://srush.github.io/annotated-s4☆456Updated last year
- Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using co…☆316Updated last year
- ☆182Updated last year
- Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions☆257Updated 10 months ago
- Unofficial JAX implementations of deep learning research papers☆150Updated 2 years ago
- Named tensors with first-class dimensions for PyTorch☆321Updated last year
- Code for our NeurIPS 2022 paper☆360Updated last year
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆204Updated last month
- A fast, effective data attribution method for neural networks in PyTorch☆170Updated this week
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch☆293Updated 9 months ago
- A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.☆546Updated 7 months ago
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆199Updated last year
- Train ImageNet *fast* in 500 lines of code with FFCV☆135Updated 4 months ago
- ☆187Updated 4 months ago
- Laplace approximations for Deep Learning.☆447Updated this week
- Code release for "Dropout Reduces Underfitting"☆311Updated last year
- Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)☆484Updated last year
- Optimal Transport Dataset Distance☆151Updated 2 years ago
- Official codebase for Pretrained Transformers as Universal Computation Engines.☆244Updated 2 years ago
- ☆202Updated 4 months ago
- ☆141Updated 10 months ago
- TorchOpt is an efficient library for differentiable optimization built upon PyTorch.☆528Updated this week
- A library to inspect and extract intermediate layers of PyTorch models.☆470Updated 2 years ago
- For optimization algorithm research and development.☆240Updated last week
- Long Range Arena for Benchmarking Efficient Transformers☆711Updated 9 months ago