The SCCS Colloquium is a forum giving students, guests, and members of the chair the opportunity to present their research insights, results, and challenges. Do you need ideas for your thesis topic? Do you want to meet your potential supervisor? Do you want to discuss your research with a diverse group of researchers, rehearse your conference talk, or simply cheer for your colleagues? Then this is the right place for you (and you are also welcome to bring your friends along).
Upcoming talks
Gizem Nur Dal: SWIM Meets KANs: Data-driven Sampling for Kolmogorov–Arnold Network Training Without Gradient Descent
SCCS Colloquium |
Kolmogorov-Arnold Networks (KANs) are a promising alternative to Multi-Layer-Perceptron (MLP) architectures. While MLPs are grounded in the Universal Approximation theorem (UAT) and learn scalar weights and biases, KANs are motivated by the Kolmogorov-Arnold Representation theorem (KART) and replace edge weights of MLPs with learnable univariate functions. Standard KANs are trained using backpropagation, which makes them slower than MLPs, since KANs learn univariate functions rather than scalar weights for each edge. Later, the Hierarchical Kolmogorov-Arnold Network (HKAN) was proposed to bypass gradient descent, locally approximating the target function at selected input points by solving a series of linear least-squares problems. However, HKAN's placement strategies for these points are target-agnostic. They depend only on the distribution of the input data, not on how the target function varies across the domain.
This thesis introduces SWIM-Guided KAN (SG-KAN), a gradient-free training framework that combines standard KANs with prior work by Bolager et al. on training MLP networks without gradient descent. In that work, input points were chosen from a carefully constructed probability distribution, giving greater weight to more important regions of the input space by sampling primarily in high-gradient regions (Sampling Where It Matters / SWIM). SG-KAN adapts SWIM's data-driven pair-sampling strategy to the univariate edge structure of KANs. Empirical analyses show that SWIM-guided sampling improves SG-KAN's accuracy over selecting random regions of the input space at each model's best configuration. Overall, SG-KAN's accuracy remains below that of HKAN and KAN on most test functions. However, it outperforms KAN by several orders of magnitude on the simplest test function. To assess the reliability of these results, a stability analysis is conducted across 50 independent runs, each with a different random seed, for each model at its best configuration. A promising direction for future work is to refine edge function construction and the projection of the SWIM-selected pair onto each input dimension, since the current axis-aligned projection approach does not account for each dimension's relative contribution to the pair's informativeness.
Master's thesis presentation. Gizem is advised by Dr. Vladyslav Fediukov.
You don't want to miss a talk? Subscribe to our mailing list and our Colloquium calendar .
Contribute a talk
To register and schedule a talk, you should fill the form Colloquium Registration at least four weeks before the earliest preferred date, at the end of a semester typically even earlier reservation is necessary due to a very high influx of presentations. Keep in mind that we only have limited slots, so please plan your presentation early! In special cases, contact colloquium@mailsccs.in.tum.de.
Colloquium sessions are now on-campus. We have booked room MI 00.13.054 for WS26/27. You can either bring your own laptop or send us the slides as a PDF ahead of time. The projector only has an HDMI connection, so please bring your own adapters if necessary.
We invite students doing their Bachelor's or Master's thesis, as well as IDP, Guided Research, or similar projects at SCCS to give one 20min presentation to discuss their results and potential future work. The time for this is typically after submitting your final text. Check also with your study program regarding any requirements for a final presentation of your project work.
New: In regular times, we will now have slots for presenting early stage projects (talk time 2-10min). This is an optional opportunity for getting additional feedback early and there is no strict timeline.
Apart from students, we also welcome doctoral candidates and guests to present their projects.
During the colloquium, things usually go as follows:
- 10min before the colloquium starts, the speakers setup their equipment with the help of the moderator. The moderator currently is Ana Cukarska. Make sure to be using an easily identifiable name in the online session's waiting room.
- The colloquium starts with an introduction to the agenda and the moderator asks the speaker's advisor/host to put the talk into context.
- Your talk starts. The scheduled time for your talk is normally 20min with additional 5-10min for discussion.
- During the discussion session, the audience can ask questions, which are meant for clarification or for putting the talk into context. The audience can also ask questions in the chat.
- Congratulations! Your talk is over and it's now time to celebrate! Have you already tried the parabolic slides that bring you from the third floor to the Magistrale?
Do you remember a talk that made you feel very happy for attending? Do you also remember a talk that confused you? What made these two experiences different?
Here are a few things to check if you want to improve your presentation:
- What is the main idea that you want people to remember after your presentation? Do you make it crystal-clear? How quickly are you arriving to it?
- Which aspects of your work can you cover in the given time frame, with a reasonable pace and good depth?
- What can you leave out (but maybe have as back-up slides) to not confuse or overwhelm the audience?
- How are you investing the crucial first two minutes of your presentation?
- How much content do you have on your slides? Is all of it important? Will the audience know which part of a slide to look at? Will somebody from the last row be able to read the content? Will somebody with limited experience in your field have time to understand what is going on?
- Are the figures clear? Are you explaining the axes or any other features clearly?
In any case, make sure to start preparing your talk early enough so that you can potentially discuss it, rehearse it, and improve it.
Here are a few good videos to find out more:
- Simon Peyton Jones: How to Give a Great Research Talk (see also How to Write a Great Research Paper)
- Susan McConnell: Designing effective scientific presentations
- Jens Weller: Presenting Code
Did you know that the TUM English Writing Center can also help you with writing good slides?
Work with us!
Do your thesis/student project in Informatics / Mathematics / Physics: Student Projects at the SCCS.