Sparse Learning
43 papers with code • 3 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Sparse Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find Sparse Learning models and implementations
ImageNet
CINIC-10
ImageNet-32
Most implemented papers
Variational Dropout Sparsifies Deep Neural Networks
ars-ashuha/variational-dropout-sparsifies-dnn
•
•
ICML 2017
We explore a recently proposed Variational Dropout technique that provided an elegant Bayesian interpretation to Gaussian Dropout.
Rigging the Lottery: Making All Tickets Winners
google-research/rigl
•
•
ICML 2020
There is a large body of work on training dense networks to yield sparse networks for inference, but this limits the size of the largest trainable sparse model to that of the largest trainable dense model.
The State of Sparsity in Deep Neural Networks
ars-ashuha/variational-dropout-sparsifies-dnn
•
•
We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet.
A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems
A commonly used approach is the Multi-Stage (MS) convex relaxation (or DC programming), which relaxes the original non-convex problem to a sequence of convex problems.
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
Shiweiliuiiiiiii/In-Time-Over-Parameterization
•
•
By starting from a random sparse network and continuously exploring sparse connectivities during training, we can perform an Over-Parameterization in the space-time manifold, closing the gap in the expressibility between sparse training and dense training.
Feature Selection: A Data Perspective
To facilitate and promote the research in this community, we also present an open-source feature selection repository that consists of most of the popular feature selection algorithms (\url{http://featureselection. asu. edu/}).
Sparse Networks from Scratch: Faster Training without Losing Performance
TimDettmers/sparse_learning
•
•
ICLR 2020
We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels.
Sparse Regression at Scale: Branch-and-Bound rooted in First-Order Optimization
In this work, we present a new exact MIP framework for $\ell_0\ell_2$-regularized regression that can scale to $p \sim 10^7$, achieving speedups of at least $5000$x, compared to state-of-the-art exact methods.
Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
Shiweiliuiiiiiii/GraNet
•
•
NeurIPS 2021
Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization).
abess: A Fast Best Subset Selection Library in Python and R
In addition, a user-friendly R library is available at the Comprehensive R Archive Network.
