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: ⓘ
- Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube☆47Updated 5 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088☆53Updated 5 years ago
- ☆29Updated 3 years ago
- Toy datasets to evaluate algorithms for domain generalization and invariance learning.☆42Updated 2 years ago
- ☆35Updated this week
- Hybrid Discriminative-Generative Training via Contrastive Learning☆75Updated last year
- Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).☆54Updated 4 years ago
- Geometric Certifications of Neural Nets☆41Updated last year
- Experiments for Meta-Learning Symmetries by Reparameterization☆55Updated 3 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 3 years ago
- Implementation of the Functional Neural Process models☆43Updated 4 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 5 years ago
- Public Codebase for Rethinking Parameter Counting: Effective Dimensionality Revisited☆35Updated last year
- Codebase for Learning Invariances in Neural Networks☆94Updated last year
- TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".☆60Updated 5 years ago
- Code for "Training Deep Energy-Based Models with f-Divergence Minimization" ICML 2020☆35Updated last year
- Limitations of the Empirical Fisher Approximation☆45Updated 4 years ago
- This repository is no longer maintained. Check☆82Updated 4 years ago
- Implementation of Invariant Risk Minimization https://arxiv.org/abs/1907.02893☆84Updated 4 years ago
- ☆55Updated 4 years ago
- The official code for Efficient Learning of Generative Models via Finite-Difference Score Matching☆12Updated last year
- ☆65Updated 5 years ago
- Code for "A Spectral Approach to Gradient Estimation for Implicit Distributions" (ICML'18)☆32Updated last year
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆33Updated 4 years ago
- ☆96Updated 2 years ago
- Reparameterize your PyTorch modules☆70Updated 3 years ago
- The codebase for the paper "A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks"☆21Updated 4 years ago
- Code from the article: "The Role of Disentanglement in Generalisation" (ICLR, 2021).☆22Updated 2 years ago
- Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight https://openreview.net/forum?id=XJk19XzGq2J☆63Updated 5 months ago