Pinned Repositories
CLaR
Concomitant Lasso with Repetitions
discrating
gen_models_dont_go_mad
Code to reproduce the experiments of the ICLR 2024 (spotlight) paper "On the Stability of Iterative Retraining of Generative Models on their Own Data" https://arxiv.org/abs/2310.00429
PersistenceImages
This project is an implemetation of the article "Persistence Images: A stable vector representation of persistent homology", Adams et al., Journal of Machine Learning Research 201, which can be found here : https://arxiv.org/pdf/1507.06217.pdf
sparse-ho
Fast hyperparameter settings for non-smooth estimators:
QB3's Repositories
QB3/sparse-ho
Fast hyperparameter settings for non-smooth estimators:
QB3/discrating
QB3/gen_models_dont_go_mad
Code to reproduce the experiments of the ICLR 2024 (spotlight) paper "On the Stability of Iterative Retraining of Generative Models on their Own Data" https://arxiv.org/abs/2310.00429
QB3/academicpages.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
QB3/agramfort.github.io
Source of my webpage
QB3/awesome-public-datasets
A topic-centric list of HQ open datasets.
QB3/benchmark_mcp
QB3/benchmark_multi_task_lasso
benchmarking of multi task lasso solvers
QB3/BlitzL1
Fast, principled L1-regularized loss minimization
QB3/BNAF
Pytorch implementation of Block Neural Autoregressive Flow
QB3/celer
Fast solver for L1-type problems: Lasso, sparse Logisitic regression, Group Lasso, weighted Lasso, Multitask Lasso, etc.
QB3/conditional-flow-matching
TorchCFM: a Conditional Flow Matching library
QB3/ddpm-torch
Unofficial PyTorch Implementation of Denoising Diffusion Probabilistic Models (DDPM)
QB3/fls
QB3/glum
High performance Python GLMs with all the features!
QB3/HAX712X
QB3/jax-meta-learning
A collection of meta-learning algorithms in Jax
QB3/jaxopt
Hardware accelerated, batchable and differentiable optimizers in JAX.
QB3/libsvmdata
QB3/MetaOptNet
Meta-Learning with Differentiable Convex Optimization (CVPR 2019 Oral)
QB3/mtl-mlopt.github.io
Website
QB3/numericalOT
QB3/optim-crash-course
QB3/OrganizationFiles
QB3/PEPit
PEPit is a package enabling computer-assisted worst-case analyses of first-order optimization methods.
QB3/QB3.github.io
QB3/results
BenchOpt benchmark results
QB3/skglm
Fast and modular sklearn replacement for generalized linear models
QB3/sparse-regression
QB3/top-sgd
Optimization algorithm which fits a ResNet to CIFAR-10 5x faster than SGD / Adam (with terrible generalization)