Author

Natansh Mathur

h-index 7 View on Semantic Scholar

We have 2 of 13 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Logarithmic-Depth Fermion Sampling: Anticoncentration and Average-Case Hardness

Sampling problems give some of the clearest conditional separations between quantum and classical computation. In Fermion Sampling, passive linear optics acts on a non-Gaussian magic input. Globally Haar-random transformations give anticoncentration and high-precision average-case hardness, but require linear depth and...

Natansh Mathur, Iordanis Kerenidis · 0 citations

#machine learning Preprint Aug 2026

"Train classical, deploy quantum"requires rethinking generalization

The results indicate that a converged moment-matching loss is not a reliable measure of generalization, and that train-classical, deploy-quantum workflows will need approaches that target generalization directly, leaving open whether better training objectives suffice or whether the model architectures themselves must...

S. Raj, Natansh Mathur, A. Perdomo-Ortiz · 0 citations