Publications

Transferable Neural Wavefunctions for Solids. / Scherbela, Michael; Gerard, Leon; Sutterud, Halvard et al.
In: Nature Computational Science, Vol. 5, No. 12, 12.2025, p. 1147–1157.

Publications: Contribution to journal › Article › Peer Reviewed

FakET: Simulating cryo-electron tomograms with neural style transfer. / Harar, Pavol (Corresponding author); Herrmann, Lukas (Corresponding author); Grohs, Philipp et al.
In: Structure, Vol. 33, No. 4, 03.04.2025, p. 820-827.

Publications: Contribution to journal › Article › Peer Reviewed

Phaseless sampling on square-root lattices. / Liehr, Lukas; Grohs, Philipp.
In: Foundations of Computational Mathematics, Vol. 25, No. 2, 04.2025, p. 351-374.

Publications: Contribution to journal › Article › Peer Reviewed

Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems. / Scherbela, Michael; Gerard, Leon; Gao, Nicolas et al.
In: Nature Computational Science, 2025.

Publications: Contribution to journal › Article › Peer Reviewed

From completeness of discrete translates to phaseless sampling of the short-time Fourier transform. / Shafkulovska, Irina; Liehr, Lukas; Grohs, Philipp.
In: Advances in Computational Mathematics, Vol. 51, No. 3, 28, 2025.

Publications: Contribution to journal › Article › Peer Reviewed

Multi-window STFT phase retrieval: lattice uniqueness. / Liehr, Lukas; Grohs, Philipp; Rathmair, Martin.
In: Journal of Functional Analysis, Vol. 288, No. 3, 110733, 2025.

Publications: Contribution to journal › Article › Peer Reviewed

Phase retrieval in Fock space and perturbation of Liouville sets. / Liehr, Lukas; Grohs, Philipp; Rathmair, Martin.
In: Revista Matematica Iberoamericana, Vol. 41, No. 3, 2025, p. 969 - 1008.

Publications: Contribution to journal › Article › Peer Reviewed

Theory-to-Practice Gap for Neural Networks and Neural Operators. / Grohs, Philipp; Lanthaler, Samuel; Trautner, Margaret.
2025.

Publications: Working paper › Preprint

Proof of the Theory-to-Practice Gap in Deep Learning via Sampling Complexity bounds for Neural Network Approximation Spaces. / Grohs, Philipp (Corresponding author); Voigtlaender, Felix.
2024. p. 1085-1143.

Publications: Working paper

Stable Gabor Phase Retrieval in Gaussian Shift-Invariant Spaces via Biorthogonality. / Liehr, Lukas; Grohs, Philipp.
In: Constructive Approximation, Vol. 59, No. 1, 02.2024, p. 61-111.

Publications: Contribution to journal › Article › Peer Reviewed

Towards a transferable fermionic neural wavefunction for molecules. / Scherbela, Michael; Gerard, Leon; Grohs, Philipp (Corresponding author).
In: Nature Communications, Vol. 15, No. 1, 120, 02.01.2024.

Publications: Contribution to journal › Article › Peer Reviewed

Deep learning variational Monte Carlo for solving the electronic Schrödinger equation. / Gerard, Leon; Grohs, Philipp; Scherbela, Michael.
Handbook of Numerical Analysis. Vol. 25 2024. p. 231 -292.

Publications: Contribution to book › Chapter › Peer Reviewed

The sampling complexity of learning invertible residual neural networks. / Li, Yuanyuan; Grohs, Philipp ; Petersen, Philipp Christian.
2024.

Publications: Working paper › Preprint

Sobolev-type embeddings for neural network approximation spaces. / Grohs, Philipp; Voigtländer, Felix.
2. ed. 2023. p. 579-599.

Publications: Working paper › Preprint

Non-uniqueness theory in sampled STFT phase retrieval. / Liehr, Lukas; Grohs, Philipp.
In: SIAM Journal on Mathematical Analysis, 21.03.2023.

Publications: Contribution to journal › Article › Peer Reviewed

Phase Transitions in Rate Distortion Theory and Deep Learning. / Grohs, Philipp; Klotz, Andreas; Voigtlaender, Felix (Corresponding author).
In: Foundations of Computational Mathematics, Vol. 23, No. 1, 02.2023, p. 329-392.

Publications: Contribution to journal › Article › Peer Reviewed

Injectivity of Gabor phase retrieval from lattice measurements. / Grohs, Philipp; Liehr, Lukas (Corresponding author).
In: Applied and Computational Harmonic Analysis, Vol. 62, 01.2023, p. 173-193.

Publications: Contribution to journal › Article › Peer Reviewed

A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations. / Grohs, Philipp; Hornung, Fabian ; Jentzen, Arnulf et al.
In: Memoirs of the American Mathematical Society, Vol. 284, No. 1410, 2023.

Publications: Contribution to journal › Article › Peer Reviewed

Arithmetic progressions and holomorphic phase retrieval. / Liehr, Lukas.
2023.

Publications: Working paper › Preprint

Learning ReLU networks to high uniform accuracy is intractable. / Berner, Julius; Grohs, Philipp; Voigtlaender, Felix.
2023. Paper presented at The Eleventh International Conference on Learning Representations: ICLR 2023.

Publications: Contribution to conference › Paper › Peer Reviewed