About Me

Adam Dziedzic

I am a postdoctoral researcher at Vector Institute and the University of Toronto, advised by Prof. Nicolas Papernot. I earned my PhD at the University of Chicago, where I was advised by Prof. Sanjay Krishnan. My goal is to empower users with data driven decisions. I worked on the Band-Limited convolutional neural networks and the DeepLens project. My previous research was focused on data loading and migration between diverse database systems within the framework of the BigDAWG project. I was an intern at Microsoft Research and worked on recommendation of hybrid physical designs (B+ tree and Columnstores) for SQL Server. I obtained my Bachelor's and Master's degrees from Warsaw University of Technology in Poland. I was also studying at DTU (Technical University of Denmark) and carried out research on databases in the DIAS group at EPFL, Switzerland. Previously, I had internships at CERN (Geneva, Switzerland), Barclays Investment Bank in London (UK), Microsoft Research (Redmond, USA) and Google (Madison, USA). I spend the rest of my waking hours on reading books, taking MOOC courses, especially on Machine & Deep Learning, enjoying many sports, playing a guitar and practicing martial-arts.

Projects and Publications

Band-limited Training and Inference For Convolutional Nerual Networks

Band-limited Training and Inference For Convolutional Nerual Networks

The convolutional layers are core building blocks of neural network architectures. In general, a convolutional filter applies to the entire frequency spectrum of the input data. We explore artificially constraining the frequency spectra of these filters and data, called band-limiting, during training. The frequency domain constraints apply to both the feed-forward and back-propagation steps. Experimentally, we observe that Convolutional Neural Networks (CNNs) are resilient to this compression scheme and results suggest that CNNs learn to leverage lower-frequency components. In particular, we found: (1) band-limited training can effectively control the resource usage (GPU and memory); (2) models trained with band-limited layers retain high prediction accuracy; and (3) requires no modification to existing training algorithms or neural network architectures to use unlike other compression schemes.

...   ...
paperpaper slidesslides talktalk bibtexbibtex
Auto-recommendation of hybrid physical designs

Auto-recommendation of hybrid physical designs

Commercial DBMSs, such as Microsoft SQL Server, cater to diverse workloads including transaction processing, decision support, and operational analytics. They also support variety in physical design structures such as B+ tree and columnstore. The benefits of B+ tree for OLTP workloads and columnstore for decision support workloads are well-understood. However, the importance of hybrid physical designs, consisting of both columnstore and B+ tree indexes on the same database, is not well-studied - a focus of this paper. We first quantify the trade-offs using carefully-crafted micro-benchmarks. This micro-benchmarking indicates that hybrid physical designs can result in orders of magnitude better performance depending on the workload. For complex real-world applications, choosing an appropriate combination of columnstore and B+ tree indexes for a database workload is challenging. We extend the Database Engine Tuning Advisor for Microsoft SQL Server to recommend a suitable combination of B+ tree and columnstore indexes for a given workload. Through extensive experiments using industry-standard benchmarks and several real-world customer workloads, we quantify how a physical design tool capable of recommending hybrid physical designs can result in orders of magnitude better execution costs compared to approaches that rely either on columnstore-only or B+ tree-only designs.

paperpaper slidesslides bibtexbibtex
BigDAWG

BigDAWG

An open source project from researchers within the Intel Science and Technology Center for Big Data (ISTC). BigDAWG is a reference implementation of a polystore database. A polystore system is any database management system (DBMS) that is built on top of multiple, heterogeneous, integrated storage engines. I worked on the scaffolding of the system and then implemented a cast operator to move data between diverse DBMSs.

...   ...
paperpaper slidesslides bibtexbibtex
Data Loading

Data Loading

An automated testing infrastructure was built to benchmark the loading performance of several commercial and open-source databases, perform an in-depth analysis to identify bottlenecks of the data loading process and investigate novel techniques which could be used to accelerate DBMS data loading.

paperpaper slidesslides bibtexbibtex

My Career

Vector Institute

Research on machine and deep learning

September 2020 - current
Postdoctoral researcher

University of Toronto

Research on machine and deep learning

September 2020 - current
Visiting researcher

University of Chicago

Research on the intersection of machine/deep learning and database management systems (DBMSs).

July 2015 - August 2020
PhD student

Google

Eliminated a performance cliff in the F1 database for the aggregation queries.

June - September 2017
PhD Software Engineering Intern at Data Infrastructure and Analysis team

Microsoft Research

Carried out research on hybrid physical designs for diverse workloads.

March - June 2015
Research Intern at Data Management, Exploration and Mining (DMX) group

EPFL

Research on data loading to diverse database management systems (DBMSs).

October 2014 - June 2015
Research Intern

Warsaw University of Technology

Student

October 2007 - September 2014
Obtained Bachelor and Master' degrees. Worked on research projects.

Barclays Investment Bank

Created a system for validating and suggesting underlyings for complex financial products.

June - August 2013
Intern Analyst

CERN

Developed a system to store information on configuration and management of non-host devices at CERN Computer Centre.

April - December 2012
Technical Student at IT Department

Mobile Startup

Worked on an app providing aspects of music social interactions.

March 2012
Udarnik

Technical University of Denmark

Student

August 2010 - January 2011
Erasmus program (took courses on logic programming, applied statistics, web 2.0 and mobile interactions, spatial databases, java programming).

Tekten

Designed a database and developed application for a telecom company in Java and PL/SQL.

July 2010
Designer and Software Engineer

Torn

Worked on a financial and accounting system project.

July - September 2009
Software Engineer

My Skills

Contact

Dziedzic Adam

PhD student at the University of Chicago

Office: JCL 299

© 2020 Adam Dziedzic