Raiden-Zhu / ICML-2023-DSGD-and-SAMLinks
[ICML 2023] Decentralized SGD and Average-direction SAM are Asymptotically Equivalent
☆20Updated 2 years ago
Alternatives and similar repositories for ICML-2023-DSGD-and-SAM
Users that are interested in ICML-2023-DSGD-and-SAM are comparing it to the libraries listed below
Sorting:
- This is the official implementation of the ICML 2023 paper - Can Forward Gradient Match Backpropagation ?☆12Updated 2 years ago
- [NeurIPS 2020 Spotlight Oral] "Training Stronger Baselines for Learning to Optimize", Tianlong Chen*, Weiyi Zhang*, Jingyang Zhou, Shiyu …☆29Updated 3 years ago
- Bi-level Optimization for Advanced Deep Learning☆47Updated 4 years ago
- [EMNLP 24] Source code for paper 'AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tu…☆12Updated last year
- [ICLR'24] "DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training" by Aochuan Chen*, Yimeng Zhang*, Jinghan Jia, James Di…☆68Updated last year
- Code for testing DCT plus Sparse (DCTpS) networks☆14Updated 4 years ago
- source code for paper "Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models"☆33Updated last year
- ☆34Updated 2 years ago
- Implementation of the SuRP algorithm by the authors of the AISTATS 2022 paper "An Information-Theoretic Justification for Model Pruning".…☆14Updated 3 years ago
- Code for "Decision-Focused Learning without Differentiable Optimization: Learning Locally Optimized Decision Losses"☆31Updated last year
- ☆13Updated 3 years ago
- Example code for paper "Bilevel Optimization: Nonasymptotic Analysis and Faster Algorithms"☆50Updated 4 years ago
- ☆73Updated last year
- Code related to ’Beyond spectral gap: The role of the topology in decentralized learning‘.☆13Updated 3 years ago
- Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?☆14Updated 3 years ago
- Repo for the paper "Landscape Surrogate Learning Decision Losses for Mathematical Optimization Under Partial Information"☆38Updated 2 years ago
- A simple Jax implementation of influence functions.☆19Updated last year
- gradient norm penalty☆41Updated last year
- SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining (NeurIPS 2024)☆38Updated last year
- ☆16Updated 2 years ago
- The official code for ICDM2023 paper: ' FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization'☆14Updated last year
- summer school materials☆46Updated 2 years ago
- Model Fusion via Optimal Transport, NeurIPS 2020☆151Updated 3 years ago
- Experiments for distributed optimization algorithms☆84Updated 2 years ago
- ☆12Updated 3 years ago
- Neural Tangent Kernel Papers☆120Updated 11 months ago
- Provably (and non-vacuously) bounding test error of deep neural networks under distribution shift with unlabeled test data.☆10Updated last year
- The code for our NeurIPS 2021 paper "Kernelized Heterogeneous Risk Minimization".☆13Updated 4 years ago
- [NeurIPS‘2021] "MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge", Geng Yuan, Xiaolong Ma, Yanzhi Wang et al…☆18Updated 3 years ago
- (ICML 2023) Feature learning in deep classifiers through Intermediate Neural Collapse: Accompanying code☆15Updated 2 years ago