marcellodebernardi / loss-landscapesLinks
Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch
☆339Updated last year
Alternatives and similar repositories for loss-landscapes
Users that are interested in loss-landscapes are comparing it to the libraries listed below
Sorting:
- Create animations for the optimization trajectory of neural nets☆158Updated last year
- Compare neural networks by their feature similarity☆370Updated 2 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆215Updated 2 months ago
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆752Updated last month
- PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 wit…☆198Updated last year
- Reproduce CKA: Similarity of Neural Network Representations Revisited☆309Updated 5 years ago
- Mode Connectivity and Fast Geometric Ensembles in PyTorch☆274Updated 2 years ago
- ☆605Updated last week
- Efficient PyTorch Hessian eigendecomposition tools!☆376Updated last year
- Train ImageNet *fast* in 500 lines of code with FFCV☆144Updated last year
- Neural Tangent Kernel Papers☆115Updated 7 months ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆351Updated 4 months ago
- ☆192Updated 4 years ago
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆425Updated 2 years ago
- Original dataset release for CIFAR-10H☆83Updated 4 years ago
- pytorch-tiny-imagenet☆180Updated last year
- This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks"…☆333Updated last year
- Optimal Transport Dataset Distance☆168Updated 3 years ago
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆278Updated 2 years ago
- ☆226Updated last year
- Continual Learning with Hypernetworks. A continual learning approach that has the flexibility to learn a dedicated set of parameters, fin…☆164Updated 3 years ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆160Updated last year
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆588Updated 8 months ago
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 4 years ago
- ☆157Updated 3 years ago
- The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from t…☆82Updated 3 years ago
- Code for "Uncertainty Estimation Using a Single Deep Deterministic Neural Network"☆272Updated 3 years ago
- PyTorch implementation of SimCLR: supports multi-GPU training and closely reproduces results☆209Updated 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…☆340Updated 2 years ago
- Code for the intrinsic dimensionality estimate of data representations☆83Updated 5 years ago