Variance reduction

Known as: Reduction 
In mathematics, more specifically in the theory of Monte Carlo methods, variance reduction is a procedure used to increase the precision of the… (More)
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Review
2017
Review
2017
Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification… (More)
  • figure 1
  • table 2
  • table 1
  • table 3
  • table 5
Is this relevant?
Highly Cited
2016
Highly Cited
2016
We study nonconvex finite-sum problems and analyze stochastic variance reduced gradient (SVRG) methods for them. SVRG and related… (More)
  • table 1
  • figure 1
  • figure 2
Is this relevant?
Highly Cited
2016
Highly Cited
2016
We consider the fundamental problem in nonconvex optimization of efficiently reaching a stationary point. In contrast to the… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
Highly Cited
2013
Highly Cited
2013
Stochastic gradient descent is popular for large scale optimization but has slow convergence asymptotically due to the inherent… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
Is this relevant?
2013
2013
Stochastic gradient optimization is a class of widely used algorithms for training machine learning models. To optimize an… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
Is this relevant?
Highly Cited
2003
Highly Cited
2003
MOTIVATION When running experiments that involve multiple high density oligonucleotide arrays, it is important to remove sources… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
Highly Cited
2002
Highly Cited
2002
Demographic stochasticity is almost universally modeled as sampling variance in a homogeneous population, although it is defined… (More)
Is this relevant?
Highly Cited
2001
Highly Cited
2001
Policy gradient methods for reinforcement learning avoid s ome of the undesirable properties of the value function approaches… (More)
  • figure 1
Is this relevant?
Highly Cited
2000
Highly Cited
2000
T paper describes, analyzes and evaluates an algorithm for estimating portfolio loss probabilities using Monte Carlo simulation… (More)
  • table 1
  • figure 1
  • table 2
  • table 3
  • table 4
Is this relevant?
Highly Cited
1996
Highly Cited
1996
Recent work has shown that combining multiple versions of unstable classifiers such as trees or neural nets results in reduced… (More)
  • table 1
  • table 2
  • table 3
  • table 4
  • table 5
Is this relevant?