r3tex / LossSurface
Efficient Neural Network Loss Landscape Generation
☆10Updated 5 years ago
Related projects: ⓘ
- Repo reproducing experimental results in "Addressing the Topological Defects of Disentanglement"☆23Updated 2 years ago
- Convolutions and more as einsum for PyTorch☆12Updated 3 months ago
- Official code for NeurIPS paper "Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach".☆16Updated 2 years ago
- Implementation of Kronecker Attention in Pytorch☆17Updated 4 years ago
- Code for 'Periodic Activation Functions Induce Stationarity' (NeurIPS 2021)☆16Updated 2 years ago
- Implementation of the Remixer Block from the Remixer paper, in Pytorch☆36Updated 2 years ago
- Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention (CVPR 2022)☆19Updated last year
- The implementation of paper ''Efficient Attention Network: Accelerate Attention by Searching Where to Plug''.☆20Updated last year
- Code base for SRSGD.☆28Updated 4 years ago
- ☆10Updated 4 years ago
- ☆16Updated last year
- ☆18Updated 3 years ago
- ☆35Updated 2 years ago
- We investigated corruption robustness across different architectures including Convolutional Neural Networks, Vision Transformers, and th…☆15Updated 2 years ago
- [TMLR 2022] Curvature access through the generalized Gauss-Newton's low-rank structure: Eigenvalues, eigenvectors, directional derivative…☆17Updated last year
- A simple implementation of a deep linear Pytorch module☆18Updated 3 years ago
- Official implementation for Neural networks with recurrent generative feedback (NeurIPS 2020).☆21Updated 3 years ago
- Successfully training approximations to full-rank matrices for efficiency in deep learning.☆16Updated 3 years ago
- Implementation for ACProp ( Momentum centering and asynchronous update for adaptive gradient methdos, NeurIPS 2021)☆15Updated 2 years ago
- ☆25Updated 4 years ago
- Implementation in the framework of my bachelor thesis: Generative Modelling using Capsule Generative Adversarial Networks☆12Updated last year
- Interpolation between Residual and Non-Residual Networks, ICML 2020. https://arxiv.org/abs/2006.05749☆26Updated 4 years ago
- Code for our ICLR Trustworthy ML 2020 workshop paper "Improved Image Wasserstein Attacks and Defenses"☆13Updated 4 years ago
- A differentiation API for PyTorch☆29Updated 4 years ago
- ☆31Updated 3 years ago
- Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube☆47Updated 5 years ago
- MintNet: Building Invertible Neural Networks with Masked Convolutions☆38Updated 3 years ago
- Reproducible code for Augmentation paper☆18Updated 5 years ago
- Self-Distillation with weighted ground-truth targets; ResNet and Kernel Ridge Regression☆17Updated 2 years ago
- Robust Optimal Transport code☆40Updated last year