Functional Constrained Optimization for Risk Aversion and Sparsity Control

10/11/2022
by   Yi Cheng, et al.
0

Risk and sparsity requirements often need to be enforced simultaneously in many applications, e.g., in portfolio optimization, assortment planning, and treatment planning. Properly balancing these potentially conflicting requirements entails the formulation of functional constrained optimization with either convex or nonconvex objectives. In this paper, we focus on projection-free methods that can generate a sparse trajectory for solving these challenging functional constrained optimization problems. Specifically, for the convex setting, we propose a Level Conditional Gradient (LCG) method, which leverages a level-set framework to update the approximation of the optimal value and an inner conditional gradient oracle (CGO) for solving mini-max subproblems. We show that the method achieves 𝒪(1/ϵ^2log1/ϵ) iteration complexity for solving both smooth and nonsmooth cases without dependency on a possibly large size of optimal dual Lagrange multiplier. For the nonconvex setting, we introduce the Level Inexact Proximal Point (IPP-LCG) method and the Direct Nonconvex Conditional Gradient (DNCG) method. The first approach taps into the advantage of LCG by transforming the problem into a series of convex subproblems and exhibits an 𝒪(1/ϵ^3log1/ϵ) iteration complexity for finding an (ϵ,ϵ)-KKT point. The DNCG is the first single-loop projection-free method, with iteration complexity bounded by 𝒪(1/ϵ^4) for computing a so-called ϵ-Wolfe point. We demonstrate the effectiveness of LCG, IPP-LCG and DNCG by devising formulations and conducting numerical experiments on two risk averse sparse optimization applications: a portfolio selection problem with and without cardinality requirement, and a radiation therapy planning problem in healthcare.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/23/2020

A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization

Nonconvex sparse models have received significant attention in high-dime...
research
06/30/2020

Conditional Gradient Methods for convex optimization with function constraints

Conditional gradient methods have attracted much attention in both machi...
research
07/07/2022

A conditional gradient homotopy method with applications to Semidefinite Programming

We propose a new homotopy-based conditional gradient method for solving ...
research
08/01/2021

Zeroth-Order Alternating Randomized Gradient Projection Algorithms for General Nonconvex-Concave Minimax Problems

In this paper, we study zeroth-order algorithms for nonconvex-concave mi...
research
10/21/2020

Efficient Projection-Free Algorithms for Saddle Point Problems

The Frank-Wolfe algorithm is a classic method for constrained optimizati...
research
07/02/2021

Screening for a Reweighted Penalized Conditional Gradient Method

The conditional gradient method (CGM) is widely used in large-scale spar...
research
02/01/2023

Accelerated First-Order Optimization under Nonlinear Constraints

We exploit analogies between first-order algorithms for constrained opti...

Please sign up or login with your details

Forgot password? Click here to reset