Explicit gradient learning for black-box optimization

Elad Sarafian, Mor Sinay, Yoram Louzoun, Noa Agmon, Sarit Kraus

פרסום מחקרי: פרק בספר / בדוח / בכנספרסום בספר כנסביקורת עמיתים


Black-Box Optimization (BBO) methods can find optimal policies for systems that interact with complex environments with no analytical representation. As such, they are of interest in many Artificial Intelligence (AI) domains. Yet classical BBO methods fall short in high-dimensional non-convex problems. They are thus often overlooked in real-world AI tasks. Here we present a BBO method, termed Explicit Gradient Learning (EGL), that is designed to optimize highdimensional ill-behaved functions. We derive EGL by finding weak spots in methods that fit the objective function with a parametric Neural Network (NN) model and obtain the gradient signal by calculating the parametric gradient. Instead of fitting the function, EGL trains a NN to estimate the objective gradient directly. We prove the convergence of EGL to a stationary point and its robustness in the optimization of integrable functions. We evaluate EGL and achieve state-ofthe- art results in two challenging problems: (1) the COCO test suite against an assortment of standard BBO methods; and (2) in a high-dimensional non-convex image generation task.

שפה מקוריתאנגלית
כותר פרסום המארח37th International Conference on Machine Learning, ICML 2020
עורכיםHal Daume, Aarti Singh
מספר עמודים11
מסת"ב (אלקטרוני)9781713821120
סטטוס פרסוםפורסם - 2020
אירוע37th International Conference on Machine Learning, ICML 2020 - Virtual, Online
משך הזמן: 13 יולי 202018 יולי 2020

סדרות פרסומים

שם37th International Conference on Machine Learning, ICML 2020


כנס37th International Conference on Machine Learning, ICML 2020
עירVirtual, Online

ASJC Scopus subject areas

  • ???subjectarea.asjc.1700.1703???
  • ???subjectarea.asjc.1700.1709???
  • ???subjectarea.asjc.1700.1712???

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Explicit gradient learning for black-box optimization'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי