Publications related to Large deviations of semisupervised learning in the stochastic block model

Related publications (26)

A coordinate transformation-based physics-informed neural networks for hyperbolic conservation laws

Hyperbolic conservation laws play a critical role in various fields, including aerodynamics, physics, and oceanography. However, traditional physics-informed neural networks (PINNs), despite their remarkable capabilities in solving partial differential equ ...

2025

Galerkin neural network-POD for acoustic and electromagnetic wave propagation in parametric domains

Jan Sickmann Hesthaven, Mariella Kast, Philipp Christoph Weder

We investigate reduced order models for acoustic and electromagnetic wave problems in parametrically defined domains. The parameter-to-solution maps are approximated following the so-called Galerkin POD-NN method, which combines the construction of a reduc ...

2025

X-ray Micro-CT based characterization of rock cuttings with deep learning

Alexandre Massoud Alahi, Pascal Turberg, Nils Frédérik Heiden Olsen

Rock cuttings from destructive boreholes are a common and cheaper source of drilling materials that can be used to determine underground geology compared to rock core samples. Classifying manually the series of cuttings can be a long and tedious process an ...

2025

Robust semantic learning for precise medical image segmentation

Seyedbehzad Bozorgtabar

Precisely localizing anomalies in medical images remains a significant challenge due to their heterogeneous nature across modalities and organs. While initial efforts excelled in identifying prominent anomalies, detecting minute target lesions posed signif ...

2025

Learning Unitaries with Quantum Statistical Queries

Armando Angrisani

We propose several algorithms for learning unitary operators from quantum statistical queries with respect to their Choi-Jamiolkowski state. Quantum statistical queries capture the capabilities of a learner with limited quantum resources, which receives as ...

VEREIN FORDERUNG OPEN ACCESS PUBLIZIERENS QUANTENWISSENSCHAF2025

Comparison of Reservoir Computing topologies using the Recurrent Kernel approach

Jonathan Yuelin Dong

Reservoir Computing (RC) has become popular in recent years thanks to its fast and efficient computational capabilities. Standard RC has been shown to be equivalent in the asymptotic limit to Recurrent Kernels, which helps in analyzing its expressive power ...

2025

Les Houches lectures on deep learning at large and infinite width

Vittorio Erba, Christian Keup

These lectures, presented at the 2022 Les Houches Summer School on Statistical Physics and Machine Learning, focus on the infinite-width limit and large-width regime of deep neural networks. Topics covered include the various statistical and dynamical prop ...

2024

IM-Context: In-Context Learning for Imbalanced Regression Tasks

Olga Fink, Ismail Nejjar

Regression models often fail to generalize effectively in regions characterized by highly imbalanced label distributions. Previous methods for deep imbalanced regression rely on gradient-based weight updates, which tend to overfit in underrepresented regio ...

Neural information processing systems foundation2024

Generative machine learning produces kinetic models that accurately characterize intracellular metabolic states

Vassily Hatzimanikatis, Ljubisa Miskovic, Subham Choudhury, Bharath Narayanan, David Michael Moret

Generating large omics datasets has become routine for gaining insights into cellular processes, yet deciphering these datasets to determine metabolic states remains challenging. Kinetic models can help integrate omics data by explicitly linking metabolite ...

Springer Science and Business Media LLC2024

Weakly nonlinear versus semi-linear models of the nonlinear evolution of the centrifugal instability

François Gallaire, Eunok Yim

We carry out a weakly nonlinear analysis of the centrifugal instability for a columnar vortex in a rotating fluid, and compare the results to those of the semi-linear model derived empirically by Yim et al. (J. Fluid Mech., vol. 897, 2020, A34). The asympt ...

Cambridge University Press2023

The inductive bias of deep learning: Connecting weights and functions

Guillermo Ortiz Jimenez

Years of a fierce competition have naturally selected the fittest deep learning algorithms. Yet, although these models work well in practice, we still lack a proper characterization of why they do so. This poses serious questions about the robustness, trus ...

EPFL2023

Variational quantum algorithm for unconstrained black box binary optimization: Application to feature selection

Julien Sebastian Gacon

We introduce a variational quantum algorithm to solve unconstrained black box binary optimization problems, i.e., problems in which the objective function is given as black box. This is in contrast to the typical setting of quantum algorithms for optimizat ...

2023

Anomaly-free scale symmetry and gravity

Mikhail Chapochnikov, Anna Tokareva

In this Letter, we address the question of whether the conformal invariance can be considered as a global symmetry of a theory of fundamental interactions. To describe Nature, this theory must contain a mechanism of spontaneous breaking of the scale symmet ...

ELSEVIER2023

van der Waals Materials for Overcoming Fundamental Limitations in Photonic Integrated Circuitry

Arslan Mazitov

With the advance of on-chip nanophotonics, there is a high demand for high-refractive-index and low-loss materials. Currently, this technology is dominated by silicon, but van der Waals (vdW) materials with a high refractive index can offer a very advanced ...

AMER CHEMICAL SOC2023

Spatiotemporal dissipative soliton resonances in multimode fiber lasers

Haoye Qin, Gang Wang

Spatiotemporal mode-locking in multimode fiber lasers is intriguing for the complex nonlinear dynamics and the increase of theoretical energy limit. In this paper, we enrich spatiotemporal mode-locking with dissipative soliton resonances, a kind of soliton ...

PERGAMON-ELSEVIER SCIENCE LTD2023

Spin, Charge, and ?-Spin Separation in One-Dimensional Photodoped Mott Insulators

Philipp Georg Werner Seeberger

We show that effectively cold metastable states in one-dimensional photodoped Mott insulators described by the extended Hubbard model exhibit spin, charge, and q-spin separation. Their wave functions in the large on-site Coulomb interaction limit can be ex ...

AMER PHYSICAL SOC2023

Non-Destructive X-Ray Imaging of Patterned Delta-Layer Devices in Silicon

Gabriel Aeppli

The progress of miniaturization in integrated electronics has led to atomic and nanometer-sized dopant devices in silicon. Such structures can be fabricated routinely by hydrogen resist lithography, using various dopants such as P and As. However, the abil ...

WILEY2023

Measurement of the Z boson production cross-section in proton-lead collisions at root(NN)-N-s=8.16 TeV

Olivier Schneider, Aurelio Bay, Guido Haefeli, Tatsuya Nakada, Frédéric Blanc, Lesya Shchutska, Mingkui Wang, François Fleuret, Chao Wang, Yi Zhang, Arnout Lodewijk M Beckers, Maxim Karpov, Liang Sun, Ian William Marison, Michael Thompson McCann, Valérie Jeanne Thérèse Renaudin-Schouler, Craig Matthew Smith, John Martin Kolinski, Simone Meloni, Achille Mauri, Basil Andrew Stansfield Davis, Chunmin Zhang, Mercedes Hannelore Rittmann-Frank, I-Chun Lin, Fabiano Colpo, Xiaoqiang Wang, Remy Jean Henry Albrecht, Xiaoqing Zhou, Marco Guarise, Yang Zou, Chia-Chun Chen, Huizhen Liu, Eliazar Rodriguez Garcia

This article presents the first measurement of the differential Z-boson production cross-section in the forward region using proton-lead collisions with the LHCb detector. The dataset was collected at a nucleon-nucleon centre-of-mass energy of root(NN)-N-s ...

Springer Nature2023

Machine-Learning-Enhanced Procedural Modeling for 4D Historical Cities Reconstruction

Frédéric Kaplan, Isabella Di Lenardo, Rémi Guillaume Petitpierre, Beatrice Vaienti

The generation of 3D models depicting cities in the past holds great potential for documentation and educational purposes. However, it is often hindered by incomplete historical data and the specialized expertise required. To address these challenges, we p ...

2023

Artificial intelligence and visual analytics in geographical space and cyberspace: Research opportunities and challenges

Stéphane Joost, François Golay

In recent decades, we have witnessed great advances on the Internet of Things, mobile devices, sensor-based systems, and resulting big data infrastructures, which have gradually, yet fundamentally influenced the way people interact with and in the digital ...

ELSEVIER2023