Sebastian Claici

PhD in Computer Science

Massachusetts Institute of Technology


I am a final year PhD student in the Geometric Data Processing Group at MIT. My research focus is on discrete optimal transport with applications to Bayesian inference, robust learning, clustering, and data summarization. During my time in GDP I’ve been lucky to collaborate with many incredible people, among them Edward Chien, Matthew Staib, Hugo Lavenant, Pierre Monteiller, Charlie Frogner, Mikhail Yurochkin, Farzaneh Mirzazadeh, and Justin Solomon.

Prior to joining Justin’s group, I was a Master’s student with Daniela Rus in the Distributed Robotics Lab where I worked on modular robotics and path planning. Before coming to MIT, I received my BSc from the University of Southampton in the United Kingdom under the supervision of Klaus-Peter Zauner.

I have done internships in interpretability of deep learning at Google, semantic segmentation with Bosch Research and Technology Center, and user experience at EPFL in Lausanne.

In my spare time, I enjoy hiking, climbing, and reviewing books I’ve read.


  • Optimal Transport
  • Convex Optimization
  • Bayesian Inference
  • Robust Learning


  • PhD in Computer Science, 2020

    Massachusetts Institute of Technology

  • SM in Computer Science, 2016

    Massachusetts Institute of Technology

  • BSc in Computer Science, 2014

    University of Southampton

Recent Publications

Alleviating Label Switching with Optimal Transport

Label switching is a phenomenon arising in mixture model posterior inference that prevents one from meaningfully assessing posterior …

Hierarchical Optimal Transport for Document Representation

The ability to measure similarity between documents enables intelligent summarization and analysis of large corpora. Past distances …

Wasserstein Coresets for Lipschitz Costs

Sparsification is becoming more and more relevant with the proliferation of huge data sets. Coresets are a principled way to construct …

Dynamical Optimal Transport on Discrete Surfaces

We propose a technique for interpolating between probability distributions on discrete surfaces, based on the theory of optimal …

Stochastic Wasserstein Barycenters

We present a stochastic algorithm to compute the barycenter of a set of probability distributions under the Wasserstein metric from …

Parallel Streaming Wasserstein Barycenters

Efficiently aggregating data from different sources is a challenging problem, particularly when samples from each source are …

Isometry Aware Preconditioning for Mesh Parameterization

This paper presents a new preconditioning technique for large-scale geometric optimization problems, inspired by applications in mesh …

Persistent Surveillance of Events with Unknown, Time-varying Statistics

We consider the problem of monitoring events occurring at discrete locations in a stochastic, time-varying manner. Our …

Distributed Aggregation for Modular Robots in the Pivoting Cube Model

We present a distributed control strategy for the aggregation of multiple modular robots into one connected structure optimized for use …

Automatic Room Segmentation from Unstructured 3D Data of Indoor Environments

We present an automatic approach for the task of reconstructing a 2D floor plan from unstructured point clouds of building interiors. …

3D M-Blocks: Self-reconfiguring robots capable of locomotion via pivoting in three dimensions

This paper presents the mechanical design of a modular robot called the 3D M-Block, a 50 mm cubic module capable of …



Software Engineering Intern, PhD


Jun 2018 – Aug 2018 Mountain View, CA
  • Research and deployment of an interpretability tool for deep neural networks.

Research Intern

Bosch Research and Technology Center

May 2016 – Aug 2016 Palo Alto, CA
  • Computer vision project on extracting architectural primitives from unstructured point cloud data.

Research Assistant

Southampton General Hospital

Jan 2014 – May 2014 Southampton, United Kingdom

Research Intern


Jun 2013 – Sep 2013 Lausanne, Switzerland

Recent Posts