Every Call is Precious: Global Optimization of Black-Box Functions with Unknown Lipschitz Constants
-
Updated
Feb 27, 2025 - Jupyter Notebook
Every Call is Precious: Global Optimization of Black-Box Functions with Unknown Lipschitz Constants
Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"
Implementation and comparison of zero order vs first order method on the AdaMM (aka AMSGrad) optimizer: analysis of convergence rates and minima shape
Implementation of defiltering techniques for blurry and noisy images
Implementation (in Python) of iterative methods for black-box image deblurring
Implementation of iterative methods for black-box image deblurring
Algorithms of zero and first order laboratory work of ITMO CT optimization course.
Stochastic optimization research conducted together with Alexander Gasnikov
Implementation of reverse filtering (or defiltering)
Add a description, image, and links to the zero-order-methods topic page so that developers can more easily learn about it.
To associate your repository with the zero-order-methods topic, visit your repo's landing page and select "manage topics."