marcellodebernardi / loss-landscapesLinks
Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch
☆343Updated 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☆159Updated last year
- Compare neural networks by their feature similarity☆374Updated 2 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆215Updated last month
- Mode Connectivity and Fast Geometric Ensembles in PyTorch☆277Updated 2 years ago
- Reproduce CKA: Similarity of Neural Network Representations Revisited☆311Updated 5 years ago
- PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 wit…☆197Updated last year
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆759Updated 3 months ago
- Efficient PyTorch Hessian eigendecomposition tools!☆379Updated last year
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆425Updated 3 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆149Updated last year
- ☆605Updated last month
- ☆193Updated 4 years ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆353Updated 5 months ago
- Optimal Transport Dataset Distance☆172Updated 3 years ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆161Updated last year
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆282Updated 2 years ago
- This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks"…☆334Updated 2 years ago
- Original dataset release for CIFAR-10H☆83Updated 4 years ago
- ☆227Updated last year
- PyTorch implementation of SimCLR: supports multi-GPU training and closely reproduces results☆208Updated last year
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆592Updated 9 months ago
- Continual Learning with Hypernetworks. A continual learning approach that has the flexibility to learn a dedicated set of parameters, fin…☆166Updated 3 years ago
- Code for coreset selection methods☆243Updated 2 years ago
- 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…☆342Updated 2 years ago
- ☆421Updated 4 years ago
- Awesome coreset/core-set/subset/sample selection works.☆181Updated last year
- Understanding Training Dynamics of Deep ReLU Networks☆298Updated this week
- Neural Tangent Kernel Papers☆117Updated 9 months ago
- A pytorch implementation of our jacobian regularizer to encourage learning representations more robust to input perturbations.☆129Updated 2 years ago
- This is a curated list for Information Bottleneck Principle, in memory of Professor Naftali Tishby.☆373Updated last year