activity
20162023
most citedSkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning

70 citations · 110 across the 4 of their papers we have counts for

collaborators
Showing cs.DBShow all

8 papers · 1 filter

cs.DB202335 cited

From BERT to GPT-3 Codex: Harnessing the Potential of Very Large Language Models for Data Management

Immanuel Trummer

Large language models have recently advanced the state of the art on many natural language processing benchmarks. The newest generation of models can be applied to a variety of tas…

cs.DB20225 cited

CodexDB: Generating Code for Processing SQL Queries using GPT-3 Codex

Immanuel Trummer

CodexDB is an SQL processing engine whose internals can be customized via natural language instructions. CodexDB is based on OpenAI's GPT-3 Codex model which translates text into c…

cs.DB2021

UDO: Universal Database Optimization using Reinforcement Learning

Junxiong Wang, Immanuel Trummer, Debabrota Basu

UDO is a versatile tool for offline tuning of database systems for specific workloads. UDO can consider a variety of tuning choices, reaching from picking transaction code variants…

cs.DB2021

Optimally Summarizing Data by Small Fact Sets for Concise Answers to Voice Queries

Immanuel Trummer, Connor Anderson

Our goal is to find combinations of facts that optimally summarize data sets. We consider this problem in the context of voice query interfaces for simple, exploratory data analysi…

cs.DB2020

Scrutinizer: A Mixed-Initiative Approach to Large-Scale, Data-Driven Claim Verification

Georgios Karagiannis, Mohammed Saeed, Paolo Papotti +1

Organizations such as the International Energy Agency (IEA) spend significant amounts of time and money to manually fact check text documents summarizing data. The goal of the Scru…

cs.DB201970 cited

SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning

Immanuel Trummer, Junxiong Wang, Deepak Maram +3

SkinnerDB is designed from the ground up for reliable join ordering. It maintains no data statistics and uses no cost or cardinality models. Instead, it uses reinforcement learning…