YSYahya Saleh

Yahya Saleh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yahya Saleh has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Adaptive Vibrational Coordinates via Symmetry-Aware Normalizing Flows

    by Emil Vogt, Álvaro Fernández Corral, Yahya Saleh

    Normalizing flows have recently been proposed to learn optimal vibrational coordinates tailored for a given molecule. It was demonstrated that such learned coordinates achieve substantial improvements in the accuracy of vibrational spectral calculations and capture essential vibrational behavior of molecules. We extend this framework to incorporate molecular symmetry by introducing a novel G-equivariant invertible residual network architecture. Exact equivariance with respect to a chosen discrete molecular symmetry group is enforced by construction, ensuring that the learned coordinate transformation respects the imposed symmetry for all network parameters. When combined with a symmetry-adapted basis, this equivariance preserves the symmetry-induced block-diagonal structure of the Hamiltonian throughout the optimization. We show that optimizing the coordinates either for a set of states spanning multiple irreducible representations or for a subset transforming according to a single irreducible representation yields comparable results. This result suggests that optimal coordinates are shared across irreducible representations and provides insight into how optimized coordinates accelerate basis convergence. The utility of symmetry-aware normalizing flows is demonstrated for H2CO and NH3.


  • Open Access

    Enhancing polynomial approximation of continuous functions by composition with homeomorphisms

    by Álvaro Fernández Corral, Yahya Saleh

    We enhance the approximation capabilities of algebraic polynomials by composing them with homeomorphisms. This composition yields families of functions that remain dense in the space of continuous functions, while enabling more accurate approximations. For univariate continuous functions exhibiting a finite number of local extrema, we prove that there exist a polynomial of finite degree and a homeomorphism whose composition approximates the target function to arbitrary accuracy. The construction is especially relevant for multivariate approximation problems, where standard numerical methods often suffer from the curse of dimensionality. To support our theoretical results, we investigate both regression tasks and the construction of molecular potential-energy surfaces, parametrizing the underlying homeomorphism using invertible neural networks. The numerical experiments show strong agreement with our theoretical analysis.

  • Open Access

    Inducing Riesz Bases in $L^2$ via Composition Operators

    by Yahya Saleh, Armin Iske

    Let $$C_h$$ C h be a composition operator mapping $$L^2(\Omega _1)$$ L 2 ( Ω 1 ) into $$L^2(\Omega _2)$$ L 2 ( Ω 2 ) for some open sets $$\Omega _1, \Omega _2 \subseteq {\mathbb {R}}^n$$ Ω 1 , Ω 2 ⊆ R n . We characterize the mappings h that transform Riesz bases of $$L^2(\Omega _1)$$ L 2 ( Ω 1 ) into Riesz bases of $$L^2(\Omega _2)$$ L 2 ( Ω 2 ) . Restricting our analysis to differentiable mappings, we demonstrate that mappings h that preserve Riesz bases have Jacobian determinants that are bounded away from zero and infinity. We discuss implications of these results for approximation theory, highlighting the potential of using bijective neural networks to construct Riesz bases with favorable approximation properties.


  • Open Access

    Transferability and interpretability of vibrational normalizing-flow coordinates

    by Emil Vogt, Álvaro Fernández Corral, Yahya Saleh, Andrey Yachmenev

    The choice of vibrational coordinates is crucial for the accuracy, efficiency, and interpretability of molecular vibrational dynamics and spectra calculations. We explore the recently proposed normalizing-flow vibrational coordinates, which are learned molecule-specific coordinate transformations optimized for a given basis set. Much like how spherical coordinates naturally simplify the hydrogen atom by embedding physical insight into the coordinate system, normalizing-flow coordinates offload complexity from the basis functions into the coordinate transformation itself. This shift not only improves basis-set convergence but also enhances the interpretability of vibrational motions. We provide an analysis of the utility, interpretation, and associated constraints of normalizing-flow vibrational coordinates. Moreover, we demonstrate that these coordinates can be generalized across different isotopologues and even structurally related molecules, achieved with minimal fine-tuning of selected output parameters.


  • Open Access

    Taylor-mode automatic differentiation for constructing molecular rovibrational Hamiltonian operators

    by Andrey Yachmenev, Emil Vogt, Álvaro Fernández Corral, Yahya Saleh

    We present an automated framework for constructing Taylor series expansions of rovibrational kinetic and potential energy operators for arbitrary molecules, internal coordinate systems, and molecular frame embedding conditions. Expressing operators in a sum-of-products form allows for computationally efficient evaluations of matrix elements in product basis sets. Our approach uses automatic differentiation tools from the Python machine learning ecosystem, particularly the JAX library, to efficiently and accurately generate high-order Taylor expansions of rovibrational operators. The implementation is available at https://github.com/robochimps/vibrojet.


  • Open Access

    Computing Excited States of Molecules Using Normalizing Flows

    by Yahya Saleh, Álvaro Fernández Corral, Emil Vogt, Armin Iske, Jochen Küpper, Andrey Yachmenev

    Calculations of highly excited and delocalized molecular vibrational states are computationally challenging tasks, which strongly depend on the choice of coordinates for describing vibrational motions. We introduce a new method that leverages normalizing flows, i.e, parametrized invertible functions, to learn optimal vibrational coordinates that satisfy the variational principle. This approach produces coordinates tailored to the vibrational problem at hand, significantly increasing the accuracy and enhancing the basis set convergence of the calculated energy spectrum. The efficiency of the method is demonstrated in calculations of the 100 lowest excited vibrational states of H2S, H2CO, and HCN/HNC. The method effectively captures the essential vibrational behavior of molecules by enhancing the separability of the Hamiltonian and hence allows for an effective assignment of approximate quantum numbers. We demonstrate that the optimized coordinates are transferable across different levels of basis set truncation, enabling a cost-efficient protocol for computing vibrational spectra of high-dimensional systems.


  • Active learning of potential-energy surfaces of weakly bound complexes with regression-tree ensembles

    by Yahya Saleh, Vishnu Sanjay, Armin Iske, Andrey Yachmenev, Jochen Küpper

    Several pool-based active learning (AL) algorithms were employed to model potential-energy surfaces (PESs) with a minimum number of electronic structure calculations. Theoretical and empirical results suggest that superior strategies can be obtained by sampling molecular structures corresponding to large uncertainties in their predictions while at the same time not deviating much from the true distribution of the data. To model PESs in an AL framework, we propose to use a regression version of stochastic query by forest, a hybrid method that samples points corresponding to large uncertainties while avoiding collecting too many points from sparse regions of space. The algorithm is implemented with decision trees that come with relatively small computational costs. We empirically show that this algorithm requires around half the data to converge to the same accuracy in comparison to the uncertainty-based query-by-committee algorithm. Moreover, the algorithm is fully automatic and does not require any prior knowledge of the PES. Simulations on a 6D PES of pyrrole(H2O) show that −1, whereas the final model with around 50 000 configurations has a generalization error of 11 cm−1.