google-parfait / dataset_grouper
Libraries for efficient and scalable group-structured dataset pipelines.
☆22Updated 5 months ago
Related projects: ⓘ
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆77Updated last year
- ☆17Updated last year
- Recycling diverse models☆42Updated last year
- Latest Weight Averaging (NeurIPS HITY 2022)☆21Updated last year
- Code for paper: "Privately generating tabular data using language models".☆14Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆52Updated last year
- ☆21Updated last year
- ☆27Updated last year
- Data for "Datamodels: Predicting Predictions with Training Data"☆87Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆34Updated last year
- Model Fusion via Optimal Transport, NeurIPS 2020☆129Updated last year
- AN EFFICIENT AND GENERAL FRAMEWORK FOR LAYERWISE-ADAPTIVE GRADIENT COMPRESSION☆10Updated 10 months ago
- ☆21Updated last year
- Code for "The Expressive Power of Low-Rank Adaptation".☆17Updated 5 months ago
- Code for "Training Neural Networks with Fixed Sparse Masks" (NeurIPS 2021).☆54Updated 2 years ago
- A simple Jax implementation of influence functions.☆15Updated 5 months ago
- Spartan is an algorithm for training sparse neural network models. This repository accompanies the paper "Spartan Differentiable Sparsity…☆24Updated last year
- ☆35Updated 2 years ago
- Deep Learning & Information Bottleneck☆45Updated last year
- Code for fast dpsgd implementations in JAX/TF☆58Updated last year
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆57Updated 3 years ago
- [ICLR 2023] Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation☆10Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆42Updated last year
- Prospect Pruning: Finding Trainable Weights at Initialization Using Meta-Gradients☆28Updated 2 years ago
- The implementation for MLSys 2023 paper: "Cuttlefish: Low-rank Model Training without All The Tuning"☆42Updated last year
- Factorized Neural Layers☆27Updated last year
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆43Updated 7 months ago
- Source code of "What can linearized neural networks actually say about generalization?☆17Updated 2 years ago
- [ICLR 2021] "Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, S…☆22Updated 2 years ago
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆14Updated 3 months ago