zeke-xie / adaptive-inertia-adai
[ICML 2022, Oral] The PyTorch Implementation of Adaptive Inertia Methods. The algorithms are based on our paper: "Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum".
☆145Updated last year
Alternatives and similar repositories for adaptive-inertia-adai:
Users that are interested in adaptive-inertia-adai are comparing it to the libraries listed below
- This is a list of peer-reviewed representative papers on deep learning dynamics (optimization dynamics of neural networks). The success o…☆259Updated 9 months ago
- [NeurIPS 2023] The PyTorch Implementation of Scheduled (Stable) Weight Decay.☆59Updated 11 months ago
- [ICML 2021] The official PyTorch Implementations of Positive-Negative Momentum Optimizers.☆28Updated 2 years ago
- [Neural Computation, MIT Press] The PyTorch Implementation of Variable Optimizers/ Neural Variable Risk Minimization proposed in our Neur…☆33Updated 3 years ago
- The pure and clear PyTorch Distributed Training Framework.☆275Updated last year
- A library for calculating the FLOPs in the forward() process based on torch.fx☆95Updated 4 months ago
- Official implementation for Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models (ICML 2022), and a re…☆106Updated 2 years ago
- The official repo for CVPR2023 highlight paper "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization".☆80Updated last year
- Official Implementation of Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction (2020)☆197Updated 2 years ago
- Code for the paper Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models (ICLR 2022 Outsta…☆170Updated 2 years ago
- Yet another PyTorch Trainer and some core components for deep learning.☆211Updated 8 months ago
- ☆186Updated last year
- [NeurIPS 2022] A novel 1-Lipschitz network that can be efficiently trained to achieve certified L-infinity robustness for free!☆30Updated 2 years ago
- ☆43Updated 4 months ago
- ☆83Updated 3 years ago
- Codes for CyGen, the novel generative modeling framework proposed in "On the Generative Utility of Cyclic Conditionals" (NeurIPS-21)☆45Updated 2 years ago
- PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)☆139Updated 2 years ago
- [ICLR 2021 top 3%] Is Attention Better Than Matrix Decomposition?☆330Updated 2 years ago
- Code repository of the paper "Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNN" https://arxiv.org/abs…☆183Updated last year
- ReduNet☆535Updated 2 years ago
- The implementation of mixup and mainfold mixup method with standard models(PreActRes, WideRes, Dense) in Cifar10, Cifar100 and SVHN datas…☆44Updated 3 years ago
- optimizer & lr scheduler & loss function collections in PyTorch☆261Updated this week
- Recent Advances in MLP-based Models (MLP is all you need!)☆113Updated 2 years ago
- Official NumPy Implementation of Deep Networks from the Principle of Rate Reduction (2021)☆60Updated 3 years ago
- a simple unofficial implementation of classifier-free diffusion guidance☆178Updated last year
- Code for reproducing results in the sliced score matching paper (UAI 2019)☆141Updated 5 years ago
- Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.☆489Updated last year
- ☆123Updated 11 months ago
- diffusion generative model☆177Updated 2 years ago
- Lossless Training Speed Up by Unbiased Dynamic Data Pruning☆324Updated 4 months ago