Seminari del Dipartimento di Matematica

ore 17:00

presso VII piano

sito convegno Fundamental Geometries

algebra e geometria

TBA

Apprenticeship Learning with Prior Beliefs: Toward Continuous-Time Inverse Optimal Control

nell'ambito della serie: STOCHASTICS AND APPLICATIONS

ore 11:00

presso - Aula Da Stabilire -

SEMINARIO INTERDISCIPLINARE

Inverse reinforcement learning seeks to recover a cost function that explains an expert’s behavior, but the problem is generally ill-posed. This talk presents a regularized inverse-optimization approach in which prior beliefs are used to select meaningful costs, even when the observed expert is not exactly optimal. After discussing the main results in the discrete setting, I develop a parallel with continuous-time stochastic control, where occupation measures, HJB inequalities, and Sobolev regularization lead naturally to an inverse PDE and variational-inequality framework.

Mathematical Advances in Federated Learning: Interaction Modeling and Clustering, Spectral Representations and Anomaly Detection

ore 14:00

presso Seminario II

Speaker's website

fisica matematica

probabilità

Federated Learning (FL) [1] trains a shared model across a population of clients that never expose their local data, replacing centralized empirical risk minimization with distributed optimization over heterogeneous, non-IID sources. The difficulty is mathematical rather than computational: the federation's behavior is governed by the structure of interactions among clients, since conflicting update directions, latent sub-populations, and adversarial or faulty participants emerge from how local data distributions relate. This talk reads these phenomena off the geometry and spectral content of client data. Interactions and clustering. I first introduce FedGWC [3], encoding pairwise client similarity in an interaction matrix built by applying a Gaussian reward to clients' empirical-loss processes. Clustering becomes the analysis of an interacting system, where clients act as particles whose mutual affinities induce homogeneous coalitions. We prove convergence of the Gaussian-weight estimators and introduce the Wasserstein Adjusted Score for cluster cohesion under class imbalance. From detection to clustering. The second part builds on the Wavelet Scattering Transform (WST) [2], a non-expansive, deformation-stable representation summarizing each client by a privacy-preserving spectral embedding computed locally before training. Waffle [4] is a supervised offline detector flagging malicious clients from these embeddings; removing the need for attack labels leads to WASA [5], an unsupervised denoising-autoencoder variant scoring deviations from a learned benign manifold and selecting clients via a Boltzmann-Gibbs sampling rule. Towards zero-shot clustering. I close with ongoing work on zero-shot clustered FL, where cluster assignment is computed offline from a client's spectral signature, with provable guarantees and no additional communication. References: [1] B. McMahan, E. Moore, D. Ramage, S. Hampson, B. Aguera y Arcas. Communication-Efficient Learning of Deep Networks from Decentralized Data. AISTATS, PMLR 54:1273-1282, 2017. [2] S. Mallat. Group Invariant Scattering. Communications on Pure and Applied Mathematics, 65(10):1331-1398, 2012. [3] A. Licciardi, D. Leo, E. Fani, B. Caputo, M. Ciccone. Interaction-Aware Gaussian Weighting for Clustered Federated Learning. Proc. 42nd Int. Conf. on Machine Learning (ICML), PMLR 267:37642-37666, 2025. [4] A. Licciardi, D. Leo, D. Carbone. Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learning. IEEE Internet of Things Journal, 2026. doi:10.1109/JIOT.2026.3671698. [5] A. Licciardi. WASA: Wavelet Scattering Autoencoders for Unsupervised Offline Detection of Malicious Clients in Federated Learning. Accepted, IEEE Int. Conf. on Omni-layer Intelligent Systems (COINS), 2026.

Tritangent planes to space sextic curves: a tropical viewpoint

nel ciclo di seminari: SEMINARIO DI ALGEBRA E GEOMETRIA

ore 12:00

presso - Aula Da Stabilire -

algebra e geometria

A classical result due to Clebsch from the mid-nineteenth century confirms that every complex space sextic curve (given as an intersection of a quadric and a cubic surface in projective 3-space) has exactly 120 tritangent planes. In this talk we will show how to use combinatorial methods arising from tropical geometry to revisit this classical problem and perform the analogous count over the reals and extensions thereof. This is joint work with Yoav Len, Hannah Markwig and Yue Ren (arXiv:2512.24277 and arXiv:2605.19905).

ore 11:15

presso Aula Seminario VIII piano

sistemi dinamici

Malliavin Calculus - Lecture 1

nel ciclo di seminari: TOPICS IN STOCHASTIC ANALYSIS: MALLIAVIN CALCULUS

ore 11:00

presso - Aula Da Stabilire -

seminario on line • collegamento al meeting

probabilità

Lecture 1

Malliavin Calculus - Lecture 2

nel ciclo di seminari: TOPICS IN STOCHASTIC ANALYSIS: MALLIAVIN CALCULUS

ore 11:00

presso - Aula Da Stabilire -

seminario on line • collegamento al meeting

probabilità

Lecture 2

Malliavin Calculus - Lecture 3

nel ciclo di seminari: TOPICS IN STOCHASTIC ANALYSIS: MALLIAVIN CALCULUS

ore 11:00

presso - Aula Da Stabilire -

seminario on line • collegamento al meeting

probabilità

Lecture 3

Malliavin Calculus - Lecture 4

nel ciclo di seminari: TOPICS IN STOCHASTIC ANALYSIS: MALLIAVIN CALCULUS

ore 11:00

presso - Aula Da Stabilire -

seminario on line • collegamento al meeting

probabilità

Lecture 4

Malliavin Calculus - Lecture 5

nel ciclo di seminari: TOPICS IN STOCHASTIC ANALYSIS: MALLIAVIN CALCULUS

ore 11:00

presso - Aula Da Stabilire -

seminario on line • collegamento al meeting

probabilità

Lecture 5

Prossimi seminari del Dipartimento di Matematica