Explicit gradient learning for black-box optimization

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

نتاج البحث: فصل من :كتاب / تقرير / مؤتمرمنشور من مؤتمرمراجعة النظراء


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.

اللغة الأصليةالإنجليزيّة
عنوان منشور المضيف37th International Conference on Machine Learning, ICML 2020
المحررونHal Daume, Aarti Singh
عدد الصفحات11
رقم المعيار الدولي للكتب (الإلكتروني)9781713821120
حالة النشرنُشِر - 2020
الحدث37th International Conference on Machine Learning, ICML 2020 - Virtual, Online
المدة: ١٣ يوليو ٢٠٢٠١٨ يوليو ٢٠٢٠

سلسلة المنشورات

الاسم37th International Conference on Machine Learning, ICML 2020
مستوى الصوتPartF168147-11


!!Conference37th International Conference on Machine Learning, ICML 2020
المدينةVirtual, Online

All Science Journal Classification (ASJC) codes

  • !!Computational Theory and Mathematics
  • !!Human-Computer Interaction
  • !!Software


أدرس بدقة موضوعات البحث “Explicit gradient learning for black-box optimization'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا