gallego-posada / constrained_sparsity
Official implementation for the paper "Controlled Sparsity via Constrained Optimization"
☆10Updated 2 years ago
Alternatives and similar repositories for constrained_sparsity:
Users that are interested in constrained_sparsity are comparing it to the libraries listed below
- Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100☆18Updated 3 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- ☆65Updated 3 months ago
- Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness☆44Updated 3 years ago
- PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)☆32Updated last week
- ☆16Updated last year
- Simple CIFAR10 ResNet example with JAX.☆23Updated 3 years ago
- ☆35Updated 2 years ago
- This is the official implementation of the ICML 2023 paper - Can Forward Gradient Match Backpropagation ?☆12Updated last year
- Optimizing neural networks via an inverse scale space flow.☆16Updated last year
- [ICLR 2023] Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation☆12Updated last year
- [ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)☆21Updated 4 months ago
- ☆11Updated 2 years ago
- Agustinus' very opiniated publication-ready plotting library☆62Updated last month
- Official repo for Trumpets: Injective Flows for Inference and Inverse Problems☆13Updated 3 years ago
- ☆12Updated 3 years ago
- ☆45Updated last year
- Code for testing DCT plus Sparse (DCTpS) networks☆14Updated 3 years ago
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆38Updated 5 years ago
- Code for 'Periodic Activation Functions Induce Stationarity' (NeurIPS 2021)☆18Updated 3 years ago
- [ICML2022] Training Your Sparse Neural Network Better with Any Mask. Ajay Jaiswal, Haoyu Ma, Tianlong Chen, ying Ding, and Zhangyang Wang☆27Updated 2 years ago
- Implicit networks can be trained efficiently and simply by using Jacobian-free Backprop (JFB).☆35Updated 3 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆74Updated 7 months ago
- ☆28Updated 3 years ago
- Spectral Tensor Train Parameterization of Deep Learning Layers☆15Updated 3 years ago
- Code to simulate energy-based neuromorphic platforms and learning algorithms for such platforms☆24Updated 3 months ago
- ☆27Updated last year
- ☆58Updated last year
- ☆32Updated 2 years ago
- EP☆16Updated 4 years ago