On Decomposing the Proximal Map
The proximal map is the key step in gradient-type algorithms, which have become prevalent in large-scale high-dimensional problems. For simple functions this proximal map is available in closed-form while for more complicated functions it can become highly nontrivial. Motivated by the need of combining regularizers to simultaneously induce different types of structures, this paper initiates a systematic investigation of when the proximal map of a sum of functions decomposes into the composition of the proximal maps of the individual summands. We not only unify a few known results scattered in the literature but also discover several new decompositions obtained almost effortlessly from our theory.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Signal Decomposition Using Masked Proximal Operators
We consider the well-studied problem of decomposing a vector time series signal into components with different characteristics, such as smooth, periodic, nonnegative, or sparse. We describe a simple and general framework…
Distributed OptimizationTime SeriesTime Series AnalysisProximal Mediation Analysis with Hidden Recanting Witnesses
Mediation analysis is essential for decomposing the causal effect of a treatment into direct and indirect pathways. However, many practical settings rely on the stringent assumption that recanting witnesses, defined as t…
Causal InferenceSemi-NMF Regularization-Based Autoencoder Training for Hyperspectral Unmixing
Hyperspectral Unmixing (HSU) refers to the procedure of decomposing measured pixel spectra into a set of constituent spectral signatures known as endmembers and a corresponding set of fractional mixing ratios. In this wo…
Hyperspectral UnmixingProximal Projection for Doubly Sparse Regularized Models
Regularization is often used in high-dimensional regression settings to generate a sparse model, which can save tremendous computing resources and identify predictors that are most strongly associated with the response. …
If Influence Functions are the Answer, Then What is the Question?
Influence functions efficiently estimate the effect of removing a single training data point on a model's learned parameters. While influence estimates align well with leave-one-out retraining for linear models, recent w…