Zobrazeno 1 - 10
of 81
pro vyhledávání: '"Trummer, Immanuel"'
We introduce {\lambda}-Tune, a framework that leverages Large Language Models (LLMs) for automated database system tuning. The design of {\lambda}-Tune is motivated by the capabilities of the latest generation of LLMs. Different from prior work, leve
Externí odkaz:
http://arxiv.org/abs/2411.03500
Autor:
Jo, Saehan, Trummer, Immanuel
The advancement of Large Language Models (LLMs) has significantly boosted performance in natural language processing (NLP) tasks. However, the deployment of high-performance LLMs incurs substantial costs, primarily due to the increased number of para
Externí odkaz:
http://arxiv.org/abs/2403.13835
The performance of worst-case optimal join algorithms depends on the order in which the join attributes are processed. Selecting good orders before query execution is hard, due to the large space of possible orders and unreliable execution cost estim
Externí odkaz:
http://arxiv.org/abs/2307.16540
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. In this paper, we present JoinGym, a lightweight and eas
Externí odkaz:
http://arxiv.org/abs/2307.11704
From BERT to GPT-3 Codex: Harnessing the Potential of Very Large Language Models for Data Management
Autor:
Trummer, Immanuel
Publikováno v:
PVLDB 2022, Volume 15, Issue 12, Pages 3770-3773
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 tasks with little to no specialized training. This technology creates var
Externí odkaz:
http://arxiv.org/abs/2306.09339
Autor:
Arora, Simran, Yang, Brandon, Eyuboglu, Sabri, Narayan, Avanika, Hojel, Andrew, Trummer, Immanuel, Ré, Christopher
A long standing goal of the data management community is to develop general, automated systems that ingest semi-structured documents and output queryable tables without human effort or domain specific customization. Given the sheer variety of potenti
Externí odkaz:
http://arxiv.org/abs/2304.09433
Autor:
Trummer, Immanuel
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 code. It is a framework on top of GPT-3 Codex that decomposes complex S
Externí odkaz:
http://arxiv.org/abs/2204.08941
Autor:
Trummer, Immanuel
DB-BERT is a database tuning tool that exploits information gained via natural language analysis of manuals and other relevant text documents. It uses text to identify database system parameters to tune as well as recommended parameter values. DB-BER
Externí odkaz:
http://arxiv.org/abs/2112.10925
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. In real-life, the feedbacks of such oracles are often noisy and avail
Externí odkaz:
http://arxiv.org/abs/2110.07232
Autor:
Trummer, Immanuel
Recent publications suggest using natural language analysis on database schema elements to guide tuning and profiling efforts. The underlying hypothesis is that state-of-the-art language processing methods, so-called language models, are able to extr
Externí odkaz:
http://arxiv.org/abs/2107.04553