Not your typical VLDB workshop

A Tutorial Workshop on Learned Algorithms, Data Structures, and Instance-Optimized Systems

Speakers

Ali Hadian To B-tree or not to B-tree: Bridging the gap between algorithmic and learned indexes	Xuanhe Zhou Logical Query Optimization	Sanjay Krishnan Learned Data Synopses: The Good, the Bad, the Ugly
Zoi Kaoudi The missing piece in ML-based query optimization	Benjamin Hilprecht Learned DBMS Components 2.0: From Workload-Driven to Zero-Shot Learning	Aishwarya Ganesan From WiscKey to Bourbon: A Learned Index for Log-Structured Merge Trees
Christina Delimitrou Leveragin ML to Handle the Increasing Complexity of the Cloud	Alekh Jindal Practical Aspects of Systems that Learn	Subarna Chatterjee A Self-Designing Storage Engine
Giorgio Vinciguerra The design of learning-based compressed data structures	Andreas Kipf Cardinality Estimation in the Learned Systems Era	Arash Termehchy Learn to Join
Justin Gottschlich Machine Programming and the Future of Software Development	Jialin Ding Instance-Optimized Indexes and Data Layouts	Ryan Marcus BAO and NEO
Umar Farooq Minhas TBD

A Tutorial As A Workshop

The workshop is intended as a tutorial of recent work on learned algorithms, data structures, and instance-optimized systems across research communities from systems to PL to theory.

A tutorial by the original authors

We will invite the original authors of - already peer reviewed - papers to present their own work. We strive to cover a diverse set of approaches from theory to systems design.

Schedule >

Speaker Nomination

We encourage everyone to nominate speakers who work in the area of ML-enhanced algorithms, data structures, and systems. Self-nominations are also welcome.

Nominate speaker >

Speaker selection

Our program committee aims to select a diverse set of speaker from all nominations. However, we will give junior researchers preference to boost their work and visibility.

Our Program Committee >

The Motivation

Over the last few years we have seen an explosion in new techniques applying Machine Learning (ML) to improve traditional algorithms, data structures, or systems in general across all fields in computer science from databases to networks and theory. For example, there has been work on improving query optimization, indexing, storage-layouts, scheduling, log-structured merge trees, sorting, compression, sketches, among many other things using ML. Arguably, the motivation behind these techniques are similar: machine learning is used to capture something about the data and/or workload to derive a better algorithm or data structure. Ultimately, what these techniques will allow us to build are “instance-optimized” systems; systems that self-adjust to a given workload and data distribution to provide unprecedented performance and avoid the need for tuning by an administrator.

As this field is moving extremely fast and is scattered around several research areas, it is increasingly harder to keep up with and start working in this area. In order to make it easier to navigate all the rapidly appearing new techniques, we are trying something: a workshop tutorial. The idea is to invite researchers, who are active in the area, to present their already published work in a survey like fashion, provide an update on what they are currently working on, and offer their take on open research questions and biggest hurdles to make the techniques practical.

Workshop Date

08/16/21

Time

09:00

The goal

A strategic goal of the workshop is to encourage a discussion between all the participants and foster new collaborations particularly for junior faculty members, PhD students and PostDocs. As VLDB will be a hybrid conference, we believe it provides a unique opportunity for such a workshop format as we plan to allow in-person as well as remote presentations. We expect that the option of remote talks will make it much more attractive for the original authors also from other research communities to accept an invitation.

Finally, we also aim to create a survey paper after the workshop and will invite all speakers to participate. While we are still in the process of figuring out all the logistic details, we believe that such a survey will be of immense value.

Nominate a speaker

We encourage everyone to nominate speakers from all computer science who work in the area of learned algorithms, data structures, and instance-optimized systems. Self-nominations are also welcome. However, we do require that the speaker has at least one peer-reviewed paper in the area and that the talk should largely focus on the already published work.

Nomination Deadline: May 1st 2021

We will send out first speaker invites as early as March, but we will keep speaker slots available at least until the deadline to be able to consider all nominations. After May 1st 2021 nominations will only be accepted if room permits.

If you are looking for a place to submit new not-yet-published work, we suggest to check-out AIDB@VLDB.