lchizat / 2020-implicit-bias-wide-2NN
Code for the paper: "Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss" (Chizat and Bach)
☆8Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for 2020-implicit-bias-wide-2NN
- Toy datasets to evaluate algorithms for domain generalization and invariance learning.☆42Updated 2 years ago
- The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) p…☆40Updated 4 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- ☆36Updated 3 years ago
- Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube☆47Updated 5 years ago
- Experiments for Meta-Learning Symmetries by Reparameterization☆56Updated 3 years ago
- Code for "A Spectral Approach to Gradient Estimation for Implicit Distributions" (ICML'18)☆32Updated last year
- TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".☆60Updated 5 years ago
- Code from the article: "The Role of Disentanglement in Generalisation" (ICLR, 2021).☆22Updated 2 years ago
- Implementation of iterative inference in deep latent variable models☆43Updated 5 years ago
- Geometric Certifications of Neural Nets☆41Updated 2 years ago
- ☆31Updated 4 years ago
- Code for the Thermodynamic Variational Objective☆26Updated 2 years ago
- The official code for Efficient Learning of Generative Models via Finite-Difference Score Matching☆12Updated 2 years ago
- Implementation of the Functional Neural Process models☆43Updated 4 years ago
- This repository is no longer maintained. Check☆82Updated 4 years ago
- Codebase for Learning Invariances in Neural Networks☆94Updated 2 years ago
- ☆53Updated 3 months ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆33Updated 4 years ago
- Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation☆69Updated 3 years ago
- Reparameterize your PyTorch modules☆72Updated 3 years ago
- ☆97Updated 2 years ago
- Recurrent Back Propagation, Back Propagation Through Optimization, ICML 2018☆39Updated 5 years ago
- Hybrid Discriminative-Generative Training via Contrastive Learning☆75Updated last year
- Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088☆53Updated 5 years ago
- Code for "Training Deep Energy-Based Models with f-Divergence Minimization" ICML 2020☆35Updated last year
- Code to implement the AND-mask and geometric mean to do gradient based optimization, from the paper "Learning explanations that are hard …☆39Updated 4 years ago
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement☆39Updated 4 years ago
- Public Codebase for Rethinking Parameter Counting: Effective Dimensionality Revisited☆36Updated last year