marcellodebernardi / loss-landscapes
Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch
☆303Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for loss-landscapes
- Create animations for the optimization trajectory of neural nets☆137Updated 9 months ago
- Mode Connectivity and Fast Geometric Ensembles in PyTorch☆265Updated 2 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆207Updated last month
- Efficient PyTorch Hessian eigendecomposition tools!☆364Updated 8 months ago
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆687Updated 7 months ago
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆266Updated last year
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆155Updated 10 months ago
- Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"☆454Updated last year
- Compare neural networks by their feature similarity☆343Updated last year
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆561Updated this week
- Reproduce CKA: Similarity of Neural Network Representations Revisited☆289Updated 4 years ago
- Neural Tangent Kernel Papers☆94Updated 8 months ago
- ☆67Updated 5 years ago
- Laplace approximations for Deep Learning.☆471Updated this week
- Train ImageNet *fast* in 500 lines of code with FFCV☆136Updated 6 months ago
- Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning, ICLR 2020☆235Updated last year
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆417Updated 2 years ago
- PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 wit…☆170Updated 9 months ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆336Updated 3 months ago
- A pytorch implementation of our jacobian regularizer to encourage learning representations more robust to input perturbations.☆123Updated last year
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆140Updated last year
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 3 years ago
- ☆186Updated 3 years ago
- Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty☆129Updated last year
- ☆219Updated 3 months ago
- Code for experiments in my blog post on the Neural Tangent Kernel: https://eigentales.com/NTK☆166Updated 5 years ago
- ☆119Updated 5 months ago
- NTK reading group☆86Updated 5 years ago
- Approximating Wasserstein distances with PyTorch☆455Updated last year
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆97Updated 4 years ago