TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

# The State of Sparsity in Deep Neural Networks

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.

17,322

# Feature Selection: A Data Perspective

29 Jan 2016jundongl/scikit-feature

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/}).

1,087

# Sparse Networks from Scratch: Faster Training without Losing Performance

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.

296

# Variational Dropout Sparsifies Deep Neural Networks

We explore a recently proposed Variational Dropout technique that provided an elegant Bayesian interpretation to Gaussian Dropout.

280

# Rigging the Lottery: Making All Tickets Winners

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.

221

# Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python

27 Jun 2020jasonge27/picasso

We describe a new library named picasso, which implements a unified framework of pathwise coordinate optimization for a variety of sparse learning problems (e. g., sparse linear regression, sparse logistic regression, sparse Poisson regression and scaled sparse linear regression) combined with efficient active set selection strategies.

60

# Fast Best Subset Selection: Coordinate Descent and Local Combinatorial Optimization Algorithms

5 Mar 2018hazimehh/L0Learn

In spite of the usefulness of $L_0$-based estimators and generic MIO solvers, there is a steep computational price to pay when compared to popular sparse learning algorithms (e. g., based on $L_1$ regularization).

56

# A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems

18 Mar 2013iancovert/Neural-GC

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.

47

# The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost

16 Jul 2019Raymw/Federated-XGBoost

Our proposed federated XGBoost algorithm incorporates data aggregation and sparse federated update processes to balance the tradeoff between privacy and learning performance.

32

# Sparse Regression at Scale: Branch-and-Bound rooted in First-Order Optimization

13 Apr 2020alisaab/l0bnb

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.

19