Dense Gradient Tree
This repository houses the supporting code for the paper Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent. The Dense Gradient Tree (DGT) technique supports learning decision trees of a given height for…
SelfTune
SelfTune is an RL framework that enables systems and service developers to automatically tune various configuration parameters and other heuristics in their codebase, rather than manually-tweaking, over time in deployment. It provides easy-to-use API (Python,…
A game-theoretic approach to provably correct and scalable offline RL
Despite increasingly widespread use of machine learning (ML) in all aspects of our lives, a broad class of scenarios still rely on automation designed by people, not artificial intelligence (AI). In real-world applications that involve…
Code Intelligence
Apply AI techniques for software engineering Code intelligence project aims to leverage AI techniques to help software developers improve the productivity of the development process. We focus on building large-scale pre-trained models to understand and…
Sumit Gulwani: 3-min video introduction
A 3-minute video introduction of Sumit Gulwani: He is a computer scientist connecting ideas, people, and research with practice. He is inventor of the Flash Fill feature in Microsoft Excel, which has now made its…
Robust Confidence Sequences
This project contains example notebooks exhibiting confidence sequences that are robust, i.e., converge for observations with infinite variance. Robust Mean Demo: The basic technique for covering the running conditional mean in a nonstationary environment. Includes…