sidak / otfusion
Model Fusion via Optimal Transport, NeurIPS 2020
☆140Updated 2 years ago
Alternatives and similar repositories for otfusion:
Users that are interested in otfusion are comparing it to the libraries listed below
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆74Updated 2 years ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆47Updated last year
- The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from t…☆77Updated 2 years ago
- Official implementation for Equivariant Architectures for Learning in Deep Weight Spaces [ICML 2023]☆86Updated last year
- Code for the paper "Efficient Dataset Distillation using Random Feature Approximation"☆37Updated 2 years ago
- Official implementation of paper Gradient Matching for Domain Generalization☆119Updated 3 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆70Updated 9 months ago
- ☆58Updated last year
- Official PyTorch implementation of "Dataset Condensation via Efficient Synthetic-Data Parameterization" (ICML'22)☆110Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- ☆107Updated last year
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 2 years ago
- ☆85Updated 2 years ago
- Code for "Supermasks in Superposition"☆121Updated last year
- ☆65Updated 2 years ago
- Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024 Spotlight]☆89Updated last week
- Awesome coreset/core-set/subset/sample selection works.☆173Updated 8 months ago
- ☆104Updated last year
- Deep Learning & Information Bottleneck☆57Updated last year
- ☆38Updated 4 months ago
- Code for "Surgical Fine-Tuning Improves Adaptation to Distribution Shifts" published at ICLR 2023☆29Updated last year
- 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
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- This repository is the official implementation of Dataset Condensation with Contrastive Signals (DCC), accepted at ICML 2022.☆20Updated 2 years ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆95Updated last year
- [NeurIPS 2024] BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models☆23Updated last month
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆79Updated last year
- Data for "Datamodels: Predicting Predictions with Training Data"☆95Updated last year
- A centralized place for deep thinking code and experiments☆82Updated last year
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆35Updated 2 years ago