Adam Dziedzic's repositories
bandlimited-cnns
Band-limited Training and Inference for Convolutional Neural Networks
adam-dziedzic.github.io
Adam Dziedzic's personal website.
awesome-ml-privacy-attacks
An awesome list of papers on privacy attacks against machine learning
private-transformers
Make differentially private training of transformers easy
albumentations
Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
DP-OPT
DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
entropy_estimators
Estimators for the entropy and other information theoretic quantities of continuous distributions
erc_template
ERC Proposal template (StG, CoG, AdG)
federated
A collection of Google research projects related to Federated Learning and Federated Analytics.
GaNDLF-1
A generalizable application framework for segmentation, regression, and classification using PyTorch
GaussianDistillation
Data-free knowledge distillation using Gaussian noise (NeurIPS paper)
imagenet18
Code to reproduce "imagenet in 18 minutes" experiments
mkultra
Prompt tuning toolkit for GPT-2 and GPT-Neo
ml-swissknife
My ML research codebase
MML-Book
Code / solutions for Mathematics for Machine Learning (MML Book)
P-tuning-v2
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
PrefixTuning
Prefix-Tuning: Optimizing Continuous Prompts for Generation
SAT-selective-cls
Self-Adaptive Traning for Selective Classification.