toshas / sttpLinks
Spectral Tensor Train Parameterization of Deep Learning Layers
☆15Updated 4 years ago
Alternatives and similar repositories for sttp
Users that are interested in sttp are comparing it to the libraries listed below
Sorting:
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆76Updated last year
- Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness☆47Updated 4 years ago
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆42Updated 6 years ago
- Padé Activation Units: End-to-end Learning of Activation Functions in Deep Neural Network☆63Updated 4 years ago
- ☆30Updated 4 years ago
- Monotone operator equilibrium networks☆53Updated 5 years ago
- Official Release of "Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling"☆49Updated 5 years ago
- Efficient Householder Transformation in PyTorch☆66Updated 4 years ago
- ☆60Updated 5 years ago
- ☆59Updated 2 years ago
- Limitations of the Empirical Fisher Approximation☆47Updated 5 months ago
- Source code for paper Conservative Uncertainty Estimation By Fitting Prior Networks (ICLR 2020)☆21Updated 2 years ago
- PyTorch implementation of FIM and empirical FIM☆61Updated 7 years ago
- Optimization with orthogonal constraints and on general manifolds☆131Updated 5 years ago
- ☆36Updated 4 years ago
- ☆47Updated 6 years ago
- Low-variance, efficient and unbiased gradient estimation for optimizing models with binary latent variables. (ICLR 2019)☆28Updated 6 years ago
- 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
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆132Updated 6 years ago
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement☆40Updated 5 years ago
- Code base for SRSGD.☆29Updated 5 years ago
- Code for "On the Spectral Bias of Neural Networks", to appear in ICML 2019 (Long Beach, CA).☆110Updated 6 years ago
- ☆54Updated last year
- Differentiable Optimizers with Perturbations in Pytorch☆68Updated 4 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆35Updated 5 years ago
- [ICML'21] Improved Contrastive Divergence Training of Energy Based Models☆63Updated 3 years ago
- ☆47Updated last year
- Contains code for the NeurIPS 2020 paper by Pan et al., "Continual Deep Learning by FunctionalRegularisation of Memorable Past"☆44Updated 4 years ago
- Gradient-based Hyperparameter Optimization Over Long Horizons☆14Updated 3 years ago
- Code accompanying our paper "Finding trainable sparse networks through Neural Tangent Transfer" to be published at ICML-2020.☆13Updated 5 years ago