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".
☆141Updated last year
Related projects ⓘ
Alternatives and complementary repositories for adaptive-inertia-adai
- This is a list of peer-reviewed representative papers on deep learning dynamics (optimization dynamics of neural networks). The success o…☆249Updated 7 months ago
- [NeurIPS 2023] The PyTorch Implementation of Scheduled (Stable) Weight Decay.☆58Updated 9 months ago
- [ICML 2021] The official PyTorch Implementations of Positive-Negative Momentum Optimizers.☆27Updated 2 years ago
- The official repo for CVPR2023 highlight paper "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization".☆77Updated last year
- ☆80Updated 3 years ago
- [Neural Computation, MIT Press] The PyTorch Implementation of Variable Optimizers/ Neural Variable Risk Minimization proposed in our Neur…☆33Updated 3 years ago
- Official implementation for Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models (ICML 2022), and a re…☆102Updated 2 years ago
- Official Implementation of Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction (2020)☆193Updated last year
- Code for the paper Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models (ICLR 2022 Outsta…☆169Updated 2 years ago
- ☆242Updated 6 months ago
- ☆181Updated 11 months ago
- [NeurIPS 2022] A novel 1-Lipschitz network that can be efficiently trained to achieve certified L-infinity robustness for free!☆30Updated 2 years ago
- Welcome to the Awesome Feature Learning in Deep Learning Thoery Reading Group! This repository serves as a collaborative platform for sch…☆144Updated 3 weeks ago
- Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.☆477Updated last year
- A library for calculating the FLOPs in the forward() process based on torch.fx☆81Updated 2 months ago
- The pure and clear PyTorch Distributed Training Framework.☆275Updated 9 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)☆138Updated 2 years ago
- Yet another PyTorch Trainer and some core components for deep learning.☆206Updated 6 months ago
- Lossless Training Speed Up by Unbiased Dynamic Data Pruning☆318Updated last month
- diffusion generative model☆170Updated 2 years ago
- Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.☆140Updated 3 years ago
- ☆39Updated last month
- ReduNet☆532Updated 2 years ago
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆42Updated 6 months ago
- [CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".☆244Updated last year
- [ICLR 2021 top 3%] Is Attention Better Than Matrix Decomposition?☆325Updated 2 years ago
- Reproduce CKA: Similarity of Neural Network Representations Revisited☆288Updated 4 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
- Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]☆207Updated 6 months ago
- Code for reproducing results in the sliced score matching paper (UAI 2019)☆140Updated 4 years ago