Ping-C / optimizer
This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent"
☆36Updated 2 years ago
Alternatives and similar repositories for optimizer:
Users that are interested in optimizer are comparing it to the libraries listed below
- Codebase for Mechanistic Mode Connectivity☆14Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- ☆52Updated 7 months ago
- ☆23Updated 2 months ago
- ☆49Updated last year
- A centralized place for deep thinking code and experiments☆83Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- ☆25Updated 2 years ago
- ☆67Updated 5 months ago
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- Latest Weight Averaging (NeurIPS HITY 2022)☆30Updated last year
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 7 months ago
- ☆26Updated 2 years ago
- Recycling diverse models☆44Updated 2 years ago
- Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight https://openreview.net/forum?id=XJk19XzGq2J☆68Updated last year
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated last year
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆47Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆56Updated last year
- ☆17Updated 2 years ago
- Pytorch Datasets for Easy-To-Hard☆27Updated 3 months ago
- Official code for the paper "Compositional Generalization from First Principles" (NeurIPS 2023)☆11Updated last year
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆62Updated 3 years ago
- ☆19Updated 9 months ago
- JAX implementation of "Fine-Tuning Language Models with Just Forward Passes"☆19Updated last year
- Deep Learning & Information Bottleneck☆60Updated last year
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- Efficient empirical NTKs in PyTorch☆18Updated 2 years ago
- Distilling Model Failures as Directions in Latent Space☆46Updated 2 years ago