Alexander Dietmüller

Supervision

I supervise Bachelor-, Semester-, and Master Theses on the topics of learning from network traffic as well as data-driven decisions in networks. Theses on the first topic can range from data science and analysis to machine learning. Theses on the second topic include areas such as congestion control design and analysis, video streaming, and network automation.

Don't hesitate to contact me if you are interested in a thesis in one of theses areas! Let me know what you are interested in, and don't forget to mention your relevant skills, previous projects, and lectures.

 

Bio

I am a fourth 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?

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 network dynamics. With the help of master students under my supervision, 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.

Aside from that, I am working on programmable packet scheduling together with Albert.

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

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

Recent Publications

A new hope for network model generalization

Alexander Dietmüller, Siddhant Ray, Romain Jacob, Laurent Vanbever

ACM HotNets 2022. Austin, Texas, USA (November 2022).

P2GO: P4 Profile-Guided Optimizations

Patrick Wintermeyer, Maria Apostolaki, Alexander Dietmüller, Laurent Vanbever

ACM HotNets 2020. Chicago, Illinois, USA (November 2020).

SP-PIFO: Approximating Push-In First-Out Behaviors using Strict-Priority Queues

Albert Gran Alcoz, Alexander Dietmüller, Laurent Vanbever

USENIX NSDI 2020. Santa Clara, California, USA (February 2020).

Supervised Theses

Advancing Predictions for Video Streaming with Transformers (S)

Lukas Röllin

Supervisors: Alexander Dietmüller, Dr. Romain Jacob, Prof. Laurent Vanbever

Gauging Risk in Resource Optimizations on Stateful Packet-Processing Devices (M)

Patrick Wintermeyer

Supervisors: Dr. Maria Apostolaki, Alexander Dietmüller, Edgar Costa Molero, Prof. Laurent Vanbever

Mailing List Analysis (S)

Lina Gehri

Supervisors: Alexander Dietmüller, Dr. Rüdiger Birkner, Prof. Laurent Vanbever

In Search of Network Shifts (B)

Fredrik Nestaas

Supervisors: Alexander Dietmüller, Dr. Romain Jacob

Traffic-Aware Compilation

Patrick Wintermeyer

Supervisors: Dr. Maria Apostolaki, Alexander Dietmüller, Prof. Laurent Vanbever

Boosting QoE in Internet Applications using Programmable Packet Scheduling (AG)

Sharat Chandra Madanapalli

Supervisors: Albert Gran Alcoz, Alexander Dietmüller, Prof. Laurent Vanbever

Improving Performance with Network-aware Scheduling Algorithms (S)

Robin Berner

Supervisors: Albert Gran Alcoz, Alexander Dietmüller, Prof. Laurent Vanbever

Network Visualization for the Routing Project (G)

Áedán Christie, Marco Di Nardo, Lina Gehri

Supervisors: Alexander Dietmüller, Prof. Laurent Vanbever

Leveraging Network Programmability for Machine Learning in the Data Plane (M)

Coralie Busse-Grawitz

Supervisors: Roland Meier, Tobias Bühler, Alexander Dietmüller, Prof. Laurent Vanbever

  • ABB Research Award 2019