EsterHlav / Dynamical-Isometry-from-Orthogonality-Neural-NetsLinks
Mathematical consequences of orthogonal weights initialization and regularization in deep learning. Experiments with gain-adjusted orthogonal regularizer on RNNs with SeqMNIST dataset.
☆17Updated 5 years ago
Alternatives and similar repositories for Dynamical-Isometry-from-Orthogonality-Neural-Nets
Users that are interested in Dynamical-Isometry-from-Orthogonality-Neural-Nets are comparing it to the libraries listed below
Sorting:
- [NeurIPS'19] [PyTorch] Adaptive Regularization in NN☆68Updated 5 years ago
- Computing various norms/measures on over-parametrized neural networks☆49Updated 6 years ago
- ☆61Updated 2 years ago
- rich posterior approximations and anomaly detection☆20Updated 6 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆35Updated 5 years ago
- [ICLR 2020] FSPool: Learning Set Representations with Featurewise Sort Pooling☆41Updated last year
- Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088☆53Updated 6 years ago
- Code for "Bridging the Gap between f-GANs and Wasserstein GANs", ICML 2020☆14Updated 5 years ago
- Implementation of Information Dropout☆39Updated 8 years ago
- Geometric Certifications of Neural Nets☆42Updated 2 years ago
- An implementation of shampoo☆77Updated 7 years ago
- ☆46Updated 6 years ago
- Code for ICML 2018 paper on "Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam" by Khan, Nielsen, Tangkaratt, Lin, …☆112Updated 6 years ago
- Code base for SRSGD.☆28Updated 5 years ago
- ☆34Updated 6 years ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Updated 4 years ago
- ☆25Updated last year
- Hybrid Discriminative-Generative Training via Contrastive Learning☆75Updated 2 years ago
- ☆45Updated 5 years ago
- A pytorch implementation for the LSTM experiments in the paper: Why Gradient Clipping Accelerates Training: A Theoretical Justification f…☆46Updated 5 years ago
- TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".☆60Updated 6 years ago
- Implementation of soft parameter sharing for neural networks☆69Updated 4 years ago
- Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube☆47Updated 5 years ago
- ☆26Updated 5 years ago
- Repository with code for paper "Inhibited Softmax for Uncertainty Estimation in Neural Networks"☆25Updated 6 years ago
- Official adversarial mixup resynthesis repository☆35Updated 5 years ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆25Updated 3 years ago
- Delta Orthogonal Initialization for PyTorch☆18Updated 7 years ago
- ☆25Updated 2 years ago
- SGD and Ordered SGD codes for deep learning, SVM, and logistic regression☆35Updated 4 years ago