Summary of Mathematics Of Statistical Sequential Decision-making: Concentration, Risk-awareness and Modelling in Stochastic Bandits, with Applications to Bariatric Surgery, by Patrick Saux
Mathematics of statistical sequential decision-making: concentration, risk-awareness and modelling in stochastic bandits, with applications to bariatric surgery
by Patrick Saux
First submitted to arxiv on: 3 May 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG); Statistics Theory (math.ST)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This thesis explores the mathematical challenges in analyzing statistical sequential decision-making algorithms for postoperative patient follow-up. It focuses on stochastic bandits, which model an agent’s learning process in an uncertain environment to maximize rewards. The study aims to develop new algorithms that balance exploitation and exploration, unlike existing industrial applications with large datasets, low-risk decisions, and clear modeling assumptions. Instead, digital health recommendations require small samples, risk-averse agents, and complex, nonparametric modeling. The researchers developed safe, anytime-valid concentration bounds, introduced a framework for risk-aware contextual bandits, and analyzed novel nonparametric bandit algorithms under weak assumptions. Empirical evidence supports the theoretical guarantees. Additionally, an interpretable machine learning model was developed with medical doctors to predict long-term weight trajectories of patients after bariatric surgery. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how computers can learn from experience in a uncertain environment. It’s about finding the best way to make decisions when there are many options and not all of them work well. The researchers created new ways for computers to balance trying what works now with trying something new that might be better later. They did this by making sure their computer programs were safe, could be used anytime, and worked well even with small amounts of data. They also made a special program that can predict how heavy patients will be after surgery. This is important because it helps doctors make good decisions for their patients. |
Keywords
» Artificial intelligence » Machine learning
