PeopleofSuperintelligence

Researcher

Erasmo Tani

Erasmo Tani is a computer scientist and mathematician whose algorithms connect graph theory, machine learning, and data science. He studied at the University of Bristol and worked on spectral sparsification in graphs in 2016, then pursued a computer science Ph.D. at Boston University from 2017 to 2019 before transferring to Chicago. In 2024, he coauthored graph-search methods with noisy predictions and faulty-oracle partition learning; AISTATS included his graph-search paper among its Outstanding Student Paper Highlights. In 2025, he coauthored work on learning hidden hypergraphs and hypergraph partitioning. Since Fall 2026, he is an assistant teaching professor at Cornell, after postdoctoral work at Sapienza and a visit to the Toyota Technological Institute at Chicago.

Timeline

  1. 2016

    A Bristol graph project

    In 2016, he studies at the University of Bristol and works on a project about spectral sparsification in graphs.

  2. 2017–2019

    Boston University and graph clustering

    From 2017 to 2019, he is a computer science PhD student at Boston University before transferring to the University of Chicago. In May 2018, a CISE seed grant funds his project with Lorenzo Orecchia and Charalampos E. Tsourakakis on graph-clustering algorithms that use edge cuts and vertex-cut information.

  3. June 2024

    Dissertation on clustering and partitioning

    In June 2024, he is scheduled to defend his University of Chicago dissertation, New Algorithmic Results in Clustering and Partitioning. It examines graph separators, hypergraph partitioning, and error-resistant learning through same-cluster queries.

  4. 2024

    Graph searching with predictions

    In 2024, he coauthors the AISTATS paper Learning-Based Algorithms for Graph Searching Problems with Adela F. DePavia and Ali Vakilian. It develops algorithms to search unknown graphs using noisy distance predictions, gives performance guarantees on unknown weighted graphs, and earns an AISTATS Outstanding Student Paper Highlight.

  5. 2024

    Fault-resistant partition learning

    In 2024, he coauthors Optimal Algorithms for Learning Partitions with Faulty Oracles with Adela Frances DePavia and Olga Medrano Martín del Campo. The paper gives algorithms for recovering a partition from same-cluster queries when an oracle can return faulty answers.

  6. 2025

    Hypergraph learning and partitioning

    In 2025, he coauthors Non-adaptive Learning of Random Hypergraphs with Queries with Bethany Austhof and Lev Reyzin; the paper studies learning a hidden hypergraph in one batch of queries and relates it to group testing. He also coauthors Submodular Hypergraph Partitioning: Metric Relaxations and Fast Algorithms via an Improved Cut-Matching Game with Antares Chen and Lorenzo Orecchia; the work uses polymatroidal cut functions to approximate directed and undirected hypergraph partitioning.

  7. By 2026

    Degrees from three universities

    By 2026, he holds a Ph.D. in computer science from the University of Chicago, an M.S. in computer science from Boston University, and an M.Eng. in mathematics and computer science from the University of Bristol.

  8. Since 2026

    Assistant teaching professor at Cornell

    In Fall 2026, he becomes an assistant teaching professor of computer science at Cornell. Before Cornell, he works as a postdoctoral researcher at Sapienza University of Rome and briefly visits the Toyota Technological Institute at Chicago. His work spans mathematical computer science and machine learning, with algorithmic solutions for computational problems in data science.

Career

  1. Since 2026Cornell UniversityAssistant Teaching Professor
  2. Sapienza University of RomePostdoctoral Researcher

Education

  1. 2024University of ChicagoPhD
  2. 2019Boston UniversityPhD student
  3. University of BristolM.Eng.

From the biography.

  1. 11% of AI doctorate holders from 2010 to 2016 founded or led a company or lab by 10 years after graduationIncludes Cornell University. We estimate how often AI doctorate holders founded or led a company or lab by 10 years after graduation, how waiting times compare between founders and top jobs, and which universities trained the most.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Cornell University. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  3. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes Cornell University. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.
  4. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Cornell University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Erasmo Tani yet. Send us a free-licensed photo.

  1. He Sun's homepage homepages.inf.ed.ac.uk. Checked 22 October 2026.
  2. Theoretical Computer Science at Boston University bu.edu. Checked 22 October 2026.
  3. CISE Seed Grant Report: Overlapping Graph Partitioning for Distributed Graph Mining bu.edu. Checked 22 October 2026.
  4. [Colloquium] Reminder - Erasmo Tani Dissertation Defense/Jun 18, 2024 mailman.cs.uchicago.edu. Checked 22 October 2026.
  5. Learning-Based Algorithms for Graph Searching Problems proceedings.mlr.press. Checked 22 October 2026.
  6. Awards | Artificial Intelligence and Statistics Conference aistats.org. Checked 22 October 2026.
  7. Optimal Algorithms for Learning Partitions with Faulty Oracles papers.nips.cc. Checked 22 October 2026.
  8. Non-adaptive Learning of Random Hypergraphs with Queries arxiv.org. Checked 22 October 2026.
  9. Submodular Hypergraph Partitioning: Metric Relaxations and Fast Algorithms via an Improved Cut-Matching Game drops.dagstuhl.de. Checked 22 October 2026.
  10. Erasmo Tani | Department of Computer Science | Cornell Bowers cs.cornell.edu. Checked 22 October 2026.