about me

I am a Miller postdoctoral fellow at UC Berkeley, hosted by Umesh Vazirani.

I do theoretical computer science, primarily quantum computing and randomized numerical linear algebra. Most of my work is on quantum learning, in the senses of “algorithms for learning properties of quantum systems” and “limitations of quantum algorithms for machine learning”.

I received my PhD at the University of Washington, advised by James Lee. Prior to that, I did my undergrad at UT Austin, where I did a thesis advised by Scott Aaronson.

[me] [CV] (last updated March 2024)

research

[google scholar] [talks and teaching]

• Structure learning of Hamiltonians from real-time evolution – Ainesh Bakshi, Allen Liu, Ankur Moitra, Ewin Tang
  FOCS 2024 [🛝]

• High-temperature Gibbs states are unentangled and efficiently preparable – Ainesh Bakshi, Allen Liu, Ankur Moitra, Ewin Tang
  FOCS 2024
  [Quanta]

• Learning quantum Hamiltonians at any temperature in polynomial time – Ainesh Bakshi, Allen Liu, Ankur Moitra, Ewin Tang
  QIP 2024 (plenary talk & best student paper award), STOC 2024 (invited to SICOMP special issue)
  [Quanta]

• Quantum machine learning without any quantum (thesis; [full pdf])

• Do you know what q-means? – João F. Doriguello, Alessandro Luongo, Ewin Tang

• An improved classical singular value transformation for quantum machine learning – Ainesh Bakshi, Ewin Tang
  SODA 2024 [🛝]

• A CS guide to the quantum singular value transformation – Ewin Tang, Kevin Tian
  SOSA 2024 [🛝]

• Query-optimal estimation of unitary channels in diamond distance – Jeongwan Haah, Robin Kothari, Ryan O’Donnell, Ewin Tang
  FOCS 2023, QIP 2024 [🛝]

• Dequantizing algorithms to understand quantum advantage in machine learning – Ewin Tang
  Nature Reviews Physics [brief survey article]

• Optimal learning of quantum Hamiltonians from high-temperature Gibbs states – Jeongwan Haah, Robin Kothari, Ewin Tang
  QIP 2022, FOCS 2022, Nature Physics (under the title Learning quantum Hamiltonians from high-temperature Gibbs states and real-time evolutions)

• An improved quantum-inspired algorithm for linear regression – András Gilyén, Zhao Song, Ewin Tang
  Quantum

• Sampling-based sublinear low-rank matrix arithmetic framework for dequantizing quantum machine learning – Nai-Hui Chia, András Gilyén, Tongyang Li, Han-Hsuan Lin, Ewin Tang, Chunhao Wang
  STOC 2020, QIP 2020, Journal of the ACM

• Quantum-inspired low-rank stochastic regression with logarithmic dependence on the dimension – András Gilyén, Seth Lloyd, Ewin Tang
  ISAAC 2020

• Quantum principal component analysis only achieves an exponential speedup because of its state preparation assumptions – Ewin Tang
  Physical Review Letters (previously known as Quantum-inspired classical algorithms for principal component analysis and supervised clustering)

• A quantum-inspired classical algorithm for recommendation systems – Ewin Tang
  QIP 2020 (plenary talk & best student paper award) combined with Quantum-inspired classical algorithms for principal component analysis and supervised clustering, STOC 2019
  Co-winner of Best Undergraduate Thesis award, advised by Scott Aaronson
  [Shtetl-Optimized] [Quanta] [UT CS] [Geekwire] [UW CSE]

• Factorizations of k-nonnegative matrices – Sunita Chepuri, Neeraja Kulkarni, Joseph Suk, Ewin Tang
  Journal of Combinatorics

contact

pronouns: she/her
email: ewin@berkeley.edu
twitter: @ewintang