讀書寫作

11/18/2022

用大數據抓用戶胃口

林步昇譯，平台假象：拆解超級平台的神話，分析數位生態系的深層特徵，建立在數位環境中不被吞噬的結構性優勢，天下雜誌，2022

Jonathan A. Knee, The Platform Delusion: Who Wins and Who Loses in the Age of Tech Titans, Portfolio, 2021.

Global Optimization via Optimal Decision Trees

Dimitris Bertsimas and Berk Öztürk, Global Optimization via Optimal Decision Trees, arXiv:2202.06017. (Code in Julia)

The global optimization literature places large emphasis on reducing intractable optimization problems into more tractable structured optimization forms. In order to achieve this goal, many existing methods are restricted to optimization over explicit constraints and objectives that use a subset of possible mathematical primitives. These are limiting in real-world contexts where more general explicit and black box constraints appear. Leveraging the dramatic speed improvements in mixed-integer optimization (MIO) and recent research in machine learning, we propose a new method to learn MIO-compatible approximations of global optimization problems using optimal decision trees with hyperplanes (OCT-Hs). This constraint learning approach only requires a bounded variable domain, and can address both explicit and inexplicit constraints. We solve the MIO approximation efficiently to find a near-optimal, near-feasible solution to the global optimization problem. We further improve the solution using a series of projected gradient descent iterations. We test the method on a number of numerical benchmarks from the literature as well as real-world design problems, demonstrating its promise in finding global optima efficiently.

Python for Data Analysis

Wes McKinney, Python for Data Analysis, O'Reilly, third edition, 2022. (Open access)

Wes McKinney is an open source software developer focusing on analytical computing. He created the Python pandas project and is a co-creator of Apache Arrow, his current focus.