Scholar
Eric R. Anschuetz
Google Scholar ID: dCjnZaUAAAAJ
Burke Fellow, Caltech
Citations & Impact
Citations
2,251
H-index
15
i10-index
21
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Average-case quantum complexity from glassiness, QIP 2026, arXiv:2510.08497 [quant-ph]
- Decoded Quantum Interferometry Requires Structure, arXiv:2509.14509 [quant-ph]
- k-Contextuality as a Heuristic for Memory Separations in Learning, IEEE International Conference on Quantum Computing and Engineering (QCE) (2025)
- Optimizing Sparse SYK, arXiv:2506.09037 [quant-ph]
- Efficient Learning Implies Quantum Glassiness, QIP 2026, arXiv:2505.00087 [quant-ph]
- Strongly Interacting Fermions Are Nontrivial yet Nonglassy, Phys. Rev. Lett. 135, 030602 (2025), QIP 2025
- A Unified Theory of Quantum Neural Network Loss Landscapes, International Conference on Learning Representations (2025)
- Bounds on the Ground State Energy of Quantum p-Spin Hamiltonians, Commun. Math. Phys. 406, 232 (2025)
- Q-CHOP: Quantum constrained Hamiltonian optimization, arXiv:2403.05653 [quant-ph]
- Arbitrary Polynomial Separations in Trainable Quantum Machine Learning, arXiv:2402.08606 [quant-ph]
- Does provable absence of barren plateaus imply classical simulability?, Nat. Commun. 16, 7907 (2025)
- The Trainability and Expressivity of Quantum Machine Learning Models, Ph.D. thesis
- Combinatorial NLTS From the Overlap Gap Property, Quantum 8, 1527 (2024)
- SupercheQ: Quantum Advantage for Distributed Databases, Tech. Rep. (Infleqtion, 2022)
- Efficient classical algorithms for simulating symmetric quantum systems, Quantum 7, 1189 (2023)
- Training Quantum Boltzmann Machines with Coresets, IEEE International Conference on Quantum Computing and Engineering (QCE) (2022)
- Interpretable Quantum Advantage in Neural Sequence Learning, PRX Quantum 4, 020338 (2023)
- Degeneracy engineering for classical and quantum annealing: A case study of sparse linear regression in collider physics, Phys. Rev. D 106, 056008 (2022)
- Quantum variational algorithms are swamped with traps, Nat. Commun. 13, 7760 (2022)
- ORQVIZ: Visualizing High-Dimensional Landscapes in Variational Quantum Algorithms, Tech. Rep. (Zapata Computing Inc., 2021)
- Critical Points in Quantum Generative Models, International Conference on Learning Representations
Research Experience
- Burke Fellow at Caltech, working on the (quantum || classical) algorithmic implications of (quantum || classical) spin glass theory.
Background
- Burke Fellow at Caltech, working on the (quantum || classical) algorithmic implications of (quantum || classical) spin glass theory. Some of his past research applied these techniques to quantum machine learning algorithms, which he showed generally fail to train due to a proliferation of poor local minima in their optimization landscapes.
Miscellany
- Personal interests and other information not provided.
Co-authors