Stochastic Gradient Descent with momentum | by Vitaly Bushaev | Towards Data Science

This is part 2 of my series on optimization algorithms used for training neural networks and machine learning models. Part 1 was about…

Solving Two-Stage Stochastic Programs in Gurobi | Towards Data Science Solving Two-Stage Stochastic Programs in Gurobi Formulating and solving a two-stage stochastic server farm problem Nakul Upadhya Oct 20, 2022 6 min read Share Photo by Taylor Vick on Unsplash Stochastic programming (SP) is a framework for modeling optimization problems that involve uncertainty [1]. In many cases, SP models take the form of a two-stage problem. The first stage involves finding the optimal deterministic decisions. These decisions are based on information we know to be certain (AKA the here-and-now decisions).

saved by

• 品翰 陳

related reading

• Stochastic optimization - Wikipediaen.wikipedia.org
• Part 3: Intro to Policy Optimization - Spinning Up documentationspinningup.openai.com
• Stochastic gradient descent - Wikipediaen.m.wikipedia.org
• Proximal Policy Optimization - Spinning Up documentationspinningup.openai.com
• GitHub - google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models.github.com
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• Optimal stopping - Wikipediaen.wikipedia.org
• Stochastic Parameter Decompositionarxiv.org
• Why GRPO is Important and How it Worksghost.oxen.ai
• Stochastic Parameter Decompositionarxiv.org
• Mathematical optimization - Wikipediaen.wikipedia.org
• Lightweight Guide to understanding GRPO and RL principles - Musings of Muraligitlostmurali.com