paper-with-me

Papers

Parameterized Convex Minorant for Objective Function Approximation in Amortized Optimization

2023-10-04 · Jinrae Kim, Youdan Kim

Parameterized convex minorant (PCM) method is proposed for the approximation of the objective function in amortized optimization. In the proposed method, the objective function approximator is expressed by the sum of a PCM and a nonnegative gap function, where the objective function approximator is bounded from below by the PCM convex in the optimization variable. The proposed objective function approximator is a universal approximator for continuous functions, and the global minimizer of the PCM attains the global minimum of the objective function approximator. Therefore, the global minimizer of the objective function approximator can be obtained by a single convex optimization. As a realization of the proposed method, extended parameterized log-sum-exp network is proposed by utilizing a parameterized log-sum-exp network as the PCM. Numerical simulation is performed for parameterized non-convex objective function approximation and for learning-based nonlinear model predictive control to demonstrate the performance and characteristics of the proposed method. The simulation results support that the proposed method can be used to learn objective functions and to find a global minimizer reliably and quickly by using convex optimization algorithms.

📄 PDF Abstract BibTeX arXiv:2310.02519

Code (1)

JinraeKim/ParametrisedConvexApproximators.jl

Tasks

Model Predictive Control

Similar Papers 제목 키워드 기반

Enhanced Low-Rank Matrix Approximation

2015-11-06 · Ankit Parekh, Ivan W. Selesnick

This letter proposes to estimate low-rank matrices by formulating a convex optimization problem with non-convex regularization. We employ parameterized non-convex penalty functions to estimate the non-zero singular value…

DenoisingImage Denoising

Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning

2021-05-26 · Chang Tian, An Liu, Guang Huang, Wu Luo

We propose a successive convex approximation based off-policy optimization (SCAOPO) algorithm to solve the general constrained reinforcement learning problem, which is formulated as a constrained Markov decision process …

reinforcement-learningReinforcement Learning (RL)

Convergence rates of the stochastic alternating algorithm for bi-objective optimization

2022-03-20 · Suyun Liu, Luis Nunes Vicente

Stochastic alternating algorithms for bi-objective optimization are considered when optimizing two conflicting functions for which optimization steps have to be applied separately for each function. Such algorithms consi…

valid

Level-Set Methods for Finite-Sum Constrained Convex Optimization

2018-07-01 · ICML 2018 7 · Qihang Lin, Runchao Ma, Tianbao Yang

We consider the constrained optimization where the objective function and the constraints are defined as summation of finitely many loss functions. This model has applications in machine learning such as Neyman-Pear…

Parameterized Convex Universal Approximators for Decision-Making Problems

2022-01-17 · Jinrae Kim, Youdan Kim

Parameterized max-affine (PMA) and parameterized log-sum-exp (PLSE) networks are proposed for general decision-making problems. The proposed approximators generalize existing convex approximators, namely, max-affine (MA)…

Decision Making