Prasanga Dhungel

Hi, I am Prasanga, a Machine Learning researcher and engineer driven by an ambition to democratize AI by prioritizing efficiency and reliability through theoretical understanding.

My journey began at the Institute of Engineering, Pulchowk Campus in Nepal, where I encountered the steep computational barriers that confine cutting-edge research to well-resourced institutions. Attempting to train custom CNNs without GPU access was a revelation—it highlighted the critical need for efficiency in modern AI. This motivated my early work on video compression using minimalistic neural networks, which achieved commercial-grade performance at a fraction of the computational cost.

I recently completed my Master’s degree in Informatics at TUM, where my thesis explored efficient methods for pruning large-scale datasets through score extrapolation under the supervision of Prof. Stephan Günnemann. My coursework spanned Deep Learning, Machine Learning, Computer Vision, and Quantum Computing—providing me with a strong theoretical foundation alongside practical skills in building production ML systems.

Currently, I work as a Machine Learning Engineer at E.ON in Munich, My time in industry—both at E.ON and previously at Naamche—exposed the stark gap between academic benchmarks and real-world application. I witnessed how models that excelled in training often faltered in deployment due to subtle calibration drifts or lacked the explainability required by stakeholders.

These experiences have shaped my research objective: we must move beyond the “scale at all costs” paradigm. I am now focused on rigorous theoretical analysis to build systems that are not just powerful, but sustainable, trustworthy, and mathematically understood.

Research Interests

The following areas represent my current research focus and published work:

Robust and Interpretable ML: Building ML systems that are not only accurate but also reliable and explainable is crucial for real-world deployment. I’m particularly interested in developing methods that handle distribution shifts, outliers, and provide meaningful explanations for model decisions—essential for domains like energy systems and critical infrastructure. The interplay between data geometry, hypothesis space and optimization dynamics dictates learnability. I thus aim to explore how data structures (such as separability), choice of architecture and loss function influence the trajectory of optimization in over-parameterized networks, and how this affects convergence and generalization.
Data-Centric AI & Efficient Learning: My master’s thesis explored novel approaches to large-scale dataset pruning through score extrapolation, addressing the computational challenges of training on massive datasets. I’m particularly interested in seeing this from the lens of data geometry and optimization dynamics, and how we can leverage this understanding to design more efficient learning algorithms. For example, Gradient descent on a linearly separable dataset converges to Hard Margin SVM solution, meaning we can essentially remove all the non-support vectors and at the end converge to the same solution (Soudry et al, 2017).
Machine Learning in Non-Euclidean Spaces: Graph neural networks and geometric deep learning open exciting possibilities for modeling complex relational data. My work has explored using geometric data structures for efficient learning, and I’m interested in applying these techniques to real-world problems involving networks, molecules, and spatial data.
MLOps & Production ML: Bridging the gap between research and production is critical. I’m passionate about building scalable ML infrastructure, implementing robust monitoring systems, and establishing best practices that enable teams to deploy and maintain ML systems reliably at scale.

If you are interested in collaborating on research projects or discussing ideas, please feel free to reach out. I am always open to exploring new challenges and opportunities to create impactful solutions.

Beyond Work

I am a lover of literature, intellectual podcasts, and the beauty of nature. In my free time, you can find me lost in a good book, exploring the Bavarian Alps, or indulging in a thought-provoking film. I’m passionate about clear communication and enjoy breaking down complex technical concepts into accessible narratives. Thank you for visiting!