Theory Seminar: Towards Optimal Algorithms for Prediction With Expert Advice

We study the classical problem of prediction with expert advice in the adversarial setting with a geometric stopping time. In 1965, Cover gave the optimal algorithm for the case of 2 experts. In this paper, we design the optimal algorithm, adversary and regret for the case of 3 experts. Further, we show that the optimal algorithm for 2 and 3 experts is a probability matching algorithm (analogous to Thompson sampling) against a particular randomized adversary.

UW Student JavaScript Programmer


UW Student JavaScript Programmer 

Short-term, Part-time & Totally Flexible Hours

Work on a small team with another computer science student on an exciting and very short-term programming project for a psychologist-entrepreneur who graduated in Psychology from the UW (‘75) All virtual work via Zoom meetings. Grad student or possibly undergrad – must be proficient with web development in JavaScript and familiar with Python development tools and the Unix shell.

Deadline: Dec. 31, 2018 

Pay: $25-45/hr depending on skill level

Activity Recognition from a First Person Perspective

Advances in sensor miniaturization, low-power computing, and battery life have enabled the first generation of mainstream wearable cameras. Millions of hours of videos have been captured by these devices, creating a record of our daily visual experiences at an unprecedented scale. This has created a major opportunity to develop new capabilities and products based on First Person Vision (FPV)--the automatic analysis of videos captured from wearable cameras. Meanwhile, vision technology is at a tipping point.

Sketching as a Tool for Efficient Networked Systems

Today, computer systems need to cope with the explosive growth of data in the world. For instance, in financial technology companies, distributed processing systems are deployed to support graph analytics, and in data-center networks, monitoring systems are used to measure traffic statistics at high speed. Ideally, we expect the systems to meet service-level objectives (SLOs) using the least amount of resource.


Subscribe to UW-Madison Computer Sciences Department RSS