Minimization Methods For Non Differentiable Functions

By J. Schulze. 2016

114 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.

Boosted Bellman Residual Minimization Handling Expert Demonstrations (2014, background): “As presented by [10], a boosting algo-rithm is a projected sub-gradient descent [22] of a convex functional in a speciﬁc functions space (here R S × A ) which has to be a Hilbert space.”
Advanced Structured Prediction (2014, methodology): “Sub-gradient method of Shor et al. (1985) , where τ t → 0 and was one of the ﬁrst optimization algorithms with convergence guarantees, independently applied by Storvik and Dahl (2000) and later by Schlesinger and Giginyak (2007) and Komodakis et al. (2007) to tackle (1.29).”
Convergence Rates for Deterministic and Stochastic Subgradient Methods Without Lipschitz Continuity (2017, methodology): “Early in the development of subgradient methods, Shor [17] observed that the normalized subgradient method (1) enjoys some form of convergence guarantee for any convex function with a nonempty set of minimizers.”
Parallel Multi-Block ADMM with o(1 / k) Convergence (2013, unknown): “A simple distributed algorithm for solving (1.1) is dual decomposition [9], which is essentially a dual ascent method or dual subgradient method [28] as follows.”