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".
☆138Updated last year
Related projects: ⓘ
- This is a list of peer-reviewed representative papers on deep learning dynamics (optimization dynamics of neural networks). The success o…☆241Updated 5 months ago
- [NeurIPS 2023] The PyTorch Implementation of Scheduled (Stable) Weight Decay.☆57Updated 7 months ago
- [ICML 2021] The official PyTorch Implementations of Positive-Negative Momentum Optimizers.☆28Updated 2 years ago
- ☆80Updated 3 years ago
- A library for calculating the FLOPs in the forward() process based on torch.fx☆72Updated 2 weeks ago
- The pure and clear PyTorch Distributed Training Framework.☆276Updated 7 months ago
- [Neural Computation, MIT Press] The PyTorch Implementation of Variable Optimizers/ Neural Variable Risk Minimization proposed in our Neur…☆34Updated 3 years ago
- The official repo for CVPR2023 highlight paper "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization".☆76Updated last year
- ☆236Updated 4 months ago
- Code for the paper Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models (ICLR 2022 Outsta…☆168Updated 2 years ago
- Recent Advances in MLP-based Models (MLP is all you need!)☆112Updated last year
- Official implementation for Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models (ICML 2022), and a re…☆102Updated 2 years ago
- PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 wit…☆167Updated 7 months ago
- Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.☆137Updated 3 years ago
- ☆170Updated 9 months ago
- Official Implementation of Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction (2020)☆190Updated last year
- Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]☆202Updated 4 months ago
- [CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".☆238Updated last year
- Unofficial implementation of MLP-Mixer: An all-MLP Architecture for Vision☆207Updated 3 years ago
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆27Updated 4 months ago
- ☆34Updated 2 months ago
- PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)☆137Updated 2 years ago
- Simple tutorials on Pytorch DDP training☆261Updated 2 years ago
- ReduNet☆531Updated 2 years ago
- diffusion generative model☆164Updated 2 years ago
- Yet another PyTorch Trainer and some core components for deep learning.☆202Updated 4 months ago
- This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."☆220Updated last year
- Lossless Training Speed Up by Unbiased Dynamic Data Pruning☆310Updated 2 weeks ago
- code to show F-Principle in the DNN training☆59Updated 2 years ago
- Official code for paper "On the Connection between Local Attention and Dynamic Depth-wise Convolution" ICLR 2022 Spotlight☆182Updated last year