Home Misc

Ari Biswas

Scientist @ Amazon : 2017-2023
PhD Student @ University of Warwick

Best way to reach me is: aribiswas3@gmail.com

CV Google Scholar Github

My CV often gets outdated, please email me for an up to date CV.

I received my undergraduate degree in Computer Engineering and Applied Mathematics under the guidance of Benjamin Snyder; Graduate Degree in Computer Science under the guidance of Robert Nowak and Rebecca Willett -from the University of Wisconsin-Madison. From 2017-2023, I was employed by Amazon under the supervision of Daniel Marcu, as a scientist to work on Amazon and Alexa search.

In July 2022, I decided to switch focus from machine learning and pursue a doctoral degree in theoretical computer science under the supervision of Graham Cormode at the University of Warwick. I was awarded the Chancellors International Scholarship, which supports my doctoral studies.

Everything I write here reflects my own thoughts and not of the people or companies I’ve worked with. My thoughts often mimick those of Eric Idle: “Bally Jerry pranged his kite right in the how’s-your-father; hairy blighter, dicky-birded, feathered back on his sammy, took a waspy, flipped over on his Betty Harpers and caught his can in the Bertie.”

News

Research

Unless specified explicitly, authors are listed in alphabetical order of last name. The * indicates the primary contributor/first author.

Verifiable Differential Privacy (To appear at CCS 2023)
Ari Biswas*, Graham Cormode
Preprint Code

Seeker: Real-Time Interactive Search
Ari Biswas*, Thai Pham, Michael Vogelsong, Houssam Nassif,
KDD 2019
Conference Paper

Adversarial principal component analysis
Daniel Pimentel*, Ari Biswas, Claudia Solís-Lemus
ISIT 2017
Conference Paper

Hands-on introduction to computer science at the freshman level. Raghuraman Balasubramanian*, Zach York, Matt Doran, Ari Biswas, Timur Girgin, Karu Sankaralingam
SIGCSE 2014
Conference Paper

Select Projects

NEXT is a computational framework and open-source machine learning system that simplifies the deployment and evaluation of active learning algorithms that use human feedback, e.g. from Mechanical Turk. The system is optimized for the real-time computational demands of active learning algorithms and built to scale to handle a crowd of workers any size. The system is for active learning researchers as well as practitioners who want to collect data adaptively.
Conference paper Github Website

Teaching

Introduction to Programming in Python, Fall. 2017
TA for Laura Hobbes Legault

Introduction to Real Analysis - Math 521, Spring. 2017
Grader/TA for Brian Cook

Introduction to Optimization CS/ECE/ISyE 524, Spring. 2016
Grader/TA for Laurent Lessard

Theory and Applications of Pattern Recognition ECE/CS 532, Fall. 2015
Grader/TA for Rob Nowak

Introduction to Computer Engineering, Spring. 2012, 2014
Lab TA for Karu Sankaralingam

Talks

Verifiable Differential Privacy
WPCSS - Warwick (2023), Amazon (2022), FOCS-Theory Day Warwick (2022)
Slides

Bandits For Online News Recommendation In Alexa AMLC (2021) - Amazon’s Internal Machine Learning Conference

Active Learning For EHR
CPCP Retreat
Talk