Search Results for author: Immanuel Trummer

Found 7 papers, 5 papers with code

SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees

1 code implementation11 Mar 2024 Saehan Jo, Immanuel Trummer

SMART employs a profiling phase that evaluates the performance of multiple LLMs to identify those that meet the user-defined accuracy level.

JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning

1 code implementation21 Jul 2023 Kaiwen Wang, Junxiong Wang, Yueying Li, Nathan Kallus, Immanuel Trummer, Wen Sun

Join order selection (JOS) is the problem of ordering join operations to minimize total query execution cost and it is the core NP-hard combinatorial optimization problem of query optimization.

Benchmarking Combinatorial Optimization +4

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

no code implementations19 Apr 2022 Immanuel Trummer

CodexDB is an SQL processing engine whose internals can be customized via natural language instructions.

DB-BERT: a Database Tuning Tool that "Reads the Manual"

no code implementations21 Dec 2021 Immanuel Trummer

DB-BERT is a database tuning tool that exploits information gained via natural language analysis of manuals and other relevant text documents.

Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback

1 code implementation14 Oct 2021 Junxiong Wang, Debabrota Basu, Immanuel Trummer

In black-box optimization problems, we aim to maximize an unknown objective function, where the function is only accessible through feedbacks of an evaluation or simulation oracle.

Can Deep Neural Networks Predict Data Correlations from Column Names?

1 code implementation9 Jul 2021 Immanuel Trummer

This paper examines that hypothesis in the context of data correlation analysis: is it possible to find column pairs with correlated data by analyzing their names via language models?

Cannot find the paper you are looking for? You can Submit a new open access paper.