Incrementally Updated Gradient Methods for Constrained and Regularized Optimization

34 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives (2014, methodology): “F (x) = f(x) + h(x), where h : R → R is convex but potentially non-differentiable, and where the proximal operation of h is easy to compute — few incremental gradient methods are applicable in this setting [3][4].”
Distributed learning with compressed gradients (2018, methodology): “If, instead, we use γ k = γ = 1 / ( Lα (1 + θ ) σ ) , then a similar argument yields that K Convergence Result of Distributed Quantized Gradient Method for Convex Optimization Theorem 8.”
On the Convergence Rate of Incremental Aggregated Gradient Algorithms (2015, methodology): “1), minx∈Rn ∑m i=1 fi(x) +h(x) with h : R → R convex and possibly nonsmooth (such as the indicator of a function when there are constraints) is simple by an additional (proximal) step; see [28].”