Publications
Preprints
Getter, Max; Trapasso, S. Ivan
The stability landscape in wave-packet scattering: geometric rigidity and sharp Sobolev thresholds Preprint
2026.
Abstract | Links | BibTeX | Tags: deformation stability, harmonic analysis, machine learning, microlocal analysis, multiscale analysis, scattering transform
@workingpaper{GT_2026,
title = {The stability landscape in wave-packet scattering: geometric rigidity and sharp Sobolev thresholds},
author = {Max Getter and S. Ivan Trapasso},
url = {https://arxiv.org/abs/2607.21578, arXiv},
year = {2026},
date = {2026-07-24},
urldate = {2026-07-24},
abstract = {A central problem in harmonic analysis is to understand how frequency resolution constrains stability under nonlinear changes of coordinates. Motivated by Mallat's wavelet scattering theory, we establish a sharp resolution--robustness principle for nonlinear representations built from two-dimensional wave-packet systems, showing that the transverse geometry of the frequency channels determines the critical Sobolev regularity. Whenever the channels are thinner than in the wavelet regime, arbitrarily small smooth deformations can move high-frequency mass between adjacent channels, producing instability already at the level of the linear filter bank and the first scattering layer. We match this obstruction with scale-sharp commutator estimates propagated through the full scattering cascade, obtaining Lipschitz stability at the critical regularity threshold. Together, the results provide the first intrinsic deformation-stability theory for non-wavelet Euclidean scattering transforms and identify a microlocal transport mechanism governing robustness across nonlinear multiscale representations.},
keywords = {deformation stability, harmonic analysis, machine learning, microlocal analysis, multiscale analysis, scattering transform},
pubstate = {published},
tppubtype = {workingpaper}
}
Journal Articles
Nicola, Fabio; Trapasso, S. Ivan
Generalized moduli of continuity under irregular or random deformations via multiscale analysis Journal Article
In: Inf. Inference, vol. 14, iss. 2, no. iaaf006, 2025.
Abstract | Links | BibTeX | Tags: deformation stability, harmonic analysis, machine learning, multiscale analysis
@article{NT_IMAIAI_25,
title = {Generalized moduli of continuity under irregular or random deformations via multiscale analysis},
author = {Fabio Nicola and S. Ivan Trapasso},
url = {https://arxiv.org/abs/2104.11977, arXiv
https://academic.oup.com/imaiai/article/doi/10.1093/imaiai/iaaf006/8108050?utm_source=authortollfreelink&utm_campaign=imaiai&utm_medium=email&guestAccessKey=87ddedf1-38c9-401d-b53d-cf41144903cf, PDF},
doi = {10.1093/imaiai/iaaf006},
year = {2025},
date = {2025-04-08},
urldate = {2025-04-08},
journal = {Inf. Inference},
volume = {14},
number = {iaaf006},
issue = {2},
abstract = {Motivated by the problem of robustness to deformations of the input for deep convolutional neural networks, we identify signal classes which are inherently stable to irregular deformations induced by distortion fields (tauin L^infty(mathbb{R}^d;mathbb{R}^d)), to be characterized in terms of a generalized modulus of continuity associated with the deformation operator. Resorting to ideas of harmonic and multiscale analysis, we prove that for signals in multiresolution approximation spaces (U_s) at scale (s), stability in (L^2) holds in the regime (|tau|_{L^infty}/sll 1) - essentially as an effect of the uncertainty principle. Instability occurs when (|tau|_{L^infty}/sgg 1), and we provide a sharp upper bound for the asymptotic growth rate. The stability results are then extended to signals in the Besov space (B^{d/2}_{2,1}) tailored to the given multiresolution approximation. We also consider the case of more general time-frequency deformations. Finally, we provide stochastic versions of the aforementioned results, namely we study the issue of stability in mean when (tau(x)) is modeled as a random field (not bounded, in general) with identically distributed variables (|tau(x)|), (xinmathbb{R}^d).},
keywords = {deformation stability, harmonic analysis, machine learning, multiscale analysis},
pubstate = {published},
tppubtype = {article}
}
Nicola, Fabio; Trapasso, S. Ivan
Stability of the scattering transform for deformations with minimal regularity Journal Article
In: J. Math. Pures Appl., vol. 180, pp. 122–150, 2023.
Abstract | Links | BibTeX | Tags: deformation stability, harmonic analysis, machine learning, multiscale analysis, scattering transform
@article{NT_JMPA_23,
title = {Stability of the scattering transform for deformations with minimal regularity},
author = {Fabio Nicola and S. Ivan Trapasso},
url = {https://arxiv.org/abs/2205.11142, arXiv
https://www.sciencedirect.com/science/article/pii/S0021782423001496/pdfft?md5=b95043909dc30fb3845bb0cac8a65b05&pid=1-s2.0-S0021782423001496-main.pdf, PDF},
doi = {10.1016/j.matpur.2023.10.008},
year = {2023},
date = {2023-12-31},
urldate = {2023-12-31},
journal = {J. Math. Pures Appl.},
volume = {180},
pages = {122–150},
publisher = {Elsevier Masson},
abstract = {Within the mathematical analysis of deep convolutional neural networks, the wavelet scattering transform introduced by Stéphane Mallat is a unique example of how the ideas of multiscale analysis can be combined with a cascade of modulus nonlinearities to build a nonexpansive, translation invariant signal representation with provable geometric stability properties, namely Lipschitz continuity to the action of small (C^2) diffeomorphisms - a remarkable result for both theoretical and practical purposes, inherently depending on the choice of the filters and their arrangement into a hierarchical architecture. In this note, we further investigate the intimate relationship between the scattering structure and the regularity of the deformation in the Hölder regularity scale (C^alpha), (alpha >0). We are able to precisely identify the stability threshold, proving that stability is still achievable for deformations of class (C^{alpha}), (alpha>1), whereas instability phenomena can occur at lower regularity levels modelled by (C^alpha), (0le alpha <1). While the behaviour at the threshold given by Lipschitz (or even (C^1)) regularity remains beyond reach, we are able to prove a stability bound in that case, up to (varepsilon) losses.},
keywords = {deformation stability, harmonic analysis, machine learning, multiscale analysis, scattering transform},
pubstate = {published},
tppubtype = {article}
}