Student Projects in LAS GroupWe offer Semester Projects, Bachelor’s and Master’s theses in our group. Depending on your preference, there are opportunities for working on theory, methods, and applications. M.Sc. projects at LAS often result in publications at leading conferences.
A list of topics for which we are actively recruiting students is given below. If you don’t see a project below that fits well, but you are interested in the kind of research our lab does, feel free to still reach out. To learn more about the research done in the group, visit our recent publications. You can also learn more about research by individual group members.
If you are interested in working with us, you can send an application by clicking the button below. Make sure that your email includes: a résumé, a recent transcript of records, your intended start date, and we highly recommend that you mention the projects you are interested in, members of the group with whom you would like to work, or recent publications by the group relevant to your interests.
If you are a bachelors or masters student but not a student at ETH, please see the opportunity listed in Applications for Summer Research Fellowships.
Current TopicsThe detailed project proposals can be downloaded only from the ETH domain.
Generalization for Meta-Learning and Personalized Federated LearningWe aim to find the correct formulation for many important problems in meta-learning and design algorithms to solve the correct formulation.
Keywords: Generalization, Meta-Learning, Personalized Federated Learning
Bayesian Optimization with PrivacyDevelop private algorithms for Bayesian Optimization and show that privacy does not come for free, it takes a toll on performance.
Keywords: Bayesian Optimization, Differential Privacy, Meta-Learning
Protein Design and Game TheoryOptimize protein design by interpreting the design process as a game.
Keywords: active learning, multi-agent learning, game theory, experiment design
Bayesian Optimization with Graph Neural NetworksEmploying Graph Neural Networks, develop a Bayesian Optimization algorithm, for problems on graph domains, which scales well with size of the domain. [At capacity for Spring semester 2023, may have openings for Fall semester.]
Keywords: Bayesian Optimization, Graph Neural Networks, Methodology, Applied
Deep Gaussian Processes on ManifoldsDevelop the analog of deep Gaussian processes for modeling manifold to manifold maps (e.g. sphere to sphere).
Keywords: Gaussian processes, deep Gaussian processes, manifolds, uncertainty, variational inference
Truly non-smooth Matérn Gaussian Processes on ManifoldsChallenging semester project: propose a non-smooth approximation for intractable manifold Matérn kernels.
Keywords: Gaussian processes, geometry, kernels, manifolds, theory
Machine Learning for Population DynamicsDesign and model spatio-temporal population dynamics using recent techniques in optimal transport and machine learning with focus on applications in single-cell biology.
Keywords: optimal transport, spatio-temporal dynamics, partial and stochastic difference equations
Learning to Schedule Energy GenerationUse machine learning to solve mixed integer programs for energy scheduling faster, in collaboration with Hitachi Energy.
Keywords: applied, discrete optimization, integer programming, graph neural networks
Maching Learning for Protein DesignLearn to find the right mutation that leads to the right enzyme.
Keywords: applied, sequence-data
Applications of Machine Learning for Choosing Crop VarietiesLearning crop variety selection and management policies from data.
Keywords: applied, uncertainty quantification, active learning, reinforcement learning, remote sensing
Assimilation of crop growth models with remote sensingMonitoring staple crops with satellite data.
Keywords: applied, remote sensing, sustainable agriculture
Meta-Learning Function Priors for Bayesian OptimizationAccelerate Bayesian optimization by meta-learning priors.
Keywords: meta-learning, active learning
Machine Learning for Converter ControlAlgorithms for control of power electronics converters, in collaboration with Hitachi Energy.
Keywords: applied, reinforcement learning, control
General AreasWe offer projects in several general areas.
- Probabilistic Approaches (Gaussian processes, Bayesian Deep Learning)
- Discrete Optimization in ML
- Online learning
- Large-Scale Machine Learning
- Active Learning
- Bayesian Optimization
- Reinforcement Learning
- Meta Learning
- Learning Theory
Examples of Previous Master Theses
BaCaDI: Bayesian Causal Discovery with Unknown InterventionsAlex Hägele with Jonas Rothfuss and Lars Lorch. AISTATS 2023. [paper]
MARS: Meta-Learning as Score Matching in the Function SpaceKruno Lehman with Jonas Rothfuss. ICLR 2023. [paper]
Neural Contextual Bandits without RegretParnian Kassraie with Andreas Krause. AISTATS 2022. [paper]
Near-Optimal Multi-Perturbation Experimental Design for Causal Structure LearningScott Sussex with Andreas Krause and Caroline Uhler. NeurIPS 2021. [paper] [blog]
DiBS: Differentiable Bayesian Structure LearningLars Lorch with Jonas Rothfuss. NeurIPS 2021. [paper] [blog]
PopSkipJump: Decision-Based Attack for Probabilistic ClassifiersNoman Ahmed Sheikh with Carl-Johann Simon-Gabriel. ICML 2021. [paper]
Icons on this page are by www.flaticon.com.