Alexander Dietmüller
PhD student

Alexander Dietmüller

I am a last-year PhD student and my research is focused on combining learning and control theory with large communication networks such as the Internet. For me, this means: (i) how can we learn the interactions between traffic and networks; and (ii) how can ensure that the data-driven decisions are optimal, in particular at the tail? I will defend my dissertation titled Adaptive Network Traffic Modeling on the 29th of July.

In my most recent project, I am tackling the issue of keeping ML models up to date with a focus on tail performance. (Re-training) ML models over time is known as continual learning (CL), and common CL systems are mostly focused on delivering good performance on average. Yet in networking, tail performance is very important, and thus I set out to develop a system that reliably identifies and remembers rare samples to improve model performance at the tail.

Furthermore, I am investigating how we can efficiently learn general network dynamics. I am investigating whether we can leverage state-of-the-art ML architectures to generalize network dynamics, i.e. extracting general patterns from a variety of traces for future predictions.

In 2022, I worked as a research intern with the Measurement Lab team at Google, supervised by Phillipa Gill and Matt Mathis.

In the past, I was working on programmable packet scheduling together with Albert and on leveraging programmable data planes to learn traffic feature distribuitions together with Georgia.

Finally, and with the help of other Master students, I also investigated various aspects of congestion control.

I received my Bachelor and Master degrees in Electrical Engineering and Information Technology from ETH Zürich.


A New Hope for Network Model Generalization


Running Theses

Supervised Theses

Make them buffer! (BA)
Student: Spencer Tellini
Supervisors: Alexander Dietmüller and Laurent Vanbever
Advancing packet-level traffic predictions with Transformers (MA)
Student: Siddhant Ray
Supervisors: Laurent Vanbever, Alexander Dietmüller, and Romain Jacob
Advancing Predictions for Video Streaming with Transformers (SA)
Student: Lukas Röllin
Supervisors: Alexander Dietmüller, Romain Jacob, and Laurent Vanbever
Gauging Risk in Resource Optimizations on Stateful Packet-Processing Devices (MA)
Student: Patrick Wintermeyer
Supervisors: Maria Apostolaki, Alexander Dietmüller, Edgar Costa Molero, and Laurent Vanbever
Mailing List Analysis (SA)
Student: Lina Gehri
Supervisors: Alexander Dietmüller, Rüdiger Birkner, and Laurent Vanbever
In Search of Network Shifts (BA)
Student: Fredrik Nestaas
Supervisors: Alexander Dietmüller and Romain Jacob
Building Your Own Internet of Microcontrollers (GA)
Student: Nicolas Adam
Supervisors: Edgar Costa Molero, Alexander Dietmüller, Roland Meier, Rui Yang, and Laurent Vanbever
Traffic-Aware Compilation (SA)
Student: Patrick Wintermeyer
Supervisors: Maria Apostolaki, Alexander Dietmüller, and Laurent Vanbever
Meta Congestion Control (SA)
Student: Boya Wang
Supervisors: Maria Apostolaki, Alexander Dietmüller, and Laurent Vanbever
Ensuring Transport Fairness with Smart Networks (SA)
Student: Long He
Supervisors: Alexander Dietmüller, Maria Apostolaki, and Laurent Vanbever
Boosting QoE in Internet Applications using Programmable Packet Scheduling (GA)
Student: Sharat Chandra Madanapalli
Supervisors: Albert Gran Alcoz, Alexander Dietmüller, and Laurent Vanbever
Improving Performance with Network-aware Scheduling Algorithms (SA)
Student: Robin Berner
Supervisors: Albert Gran Alcoz, Alexander Dietmüller, and Laurent Vanbever
Network Visualization for the Routing Project (GA)
Student: Áedán Christie, Marco Di Nardo, Lina Gehri
Supervisors: Alexander Dietmüller and Laurent Vanbever
Leveraging Network Programmability for Machine Learning in the Data Plane (MA)
Student: Coralie Busse-Grawitz
Supervisors: Roland Meier, Tobias Bühler, Alexander Dietmüller, and Laurent Vanbever