Edouard Pauwels

75 papers A* 10Journal 62Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	An analytic theory of convolutional neural network inverse problems solvers. CoRR Minh Hai Nguyen, Quoc Bao Do, Edouard Pauwels, Pierre Weiss
2026	J	`jnl`	Geometric and computational hardness of bilevel programming. Math. Program. Jérôme Bolte, Quoc-Tung Le, Edouard Pauwels, Samuel Vaiter
2026	J	`jnl`	The adjoint state method for parametric definable optimization without smoothness or uniqueness. CoRR Jérôme Bolte, Edouard Pauwels, Cheik Traoré
2025	J	`jnl`	A second-order-like optimizer with adaptive gradient scaling for deep learning. Trans. Mach. Learn. Res. Jérôme Bolte, Ryan Boustany, Edouard Pauwels, Andrei I. Purica
2025	J	`jnl`	Convergence of optimizers implies eigenvalues filtering at equilibrium. CoRR Jérôme Bolte, Quoc-Tung Le, Edouard Pauwels
2025	J	`jnl`	How Diffusion Prior Landscapes Shape the Posterior in Blind Deconvolution. CoRR Minh-Hai Nguyen, Edouard Pauwels, Pierre Weiss
2025	J	`jnl`	Learning Theory for Kernel Bilevel Optimization. CoRR Fares El Khoury, Edouard Pauwels, Samuel Vaiter, Michael Arbel
2024	J	`jnl`	A second-order-like optimizer with adaptive gradient scaling for deep learning. CoRR Jérôme Bolte, Ryan Boustany, Edouard Pauwels, Andrei I. Purica
2024	A*	`conf`	Derivatives of Stochastic Gradient Descent in parametric optimization. NeurIPS Franck Iutzeler, Edouard Pauwels, Samuel Vaiter
2024	J	`jnl`	Derivatives of Stochastic Gradient Descent. CoRR Franck Iutzeler, Edouard Pauwels, Samuel Vaiter
2024	J	`jnl`	Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems. SIAM J. Optim. Jérôme Bolte, Edouard Pauwels, Antonio Silveti-Falls
2024	J	`jnl`	Geometric and computational hardness of bilevel programming. CoRR Jérôme Bolte, Quoc-Tung Le, Edouard Pauwels, Samuel Vaiter
2024	J	`jnl`	On the nature of Bregman functions. Oper. Res. Lett. Edouard Pauwels
2024	J	`jnl`	The Iterates of the Frank-Wolfe Algorithm May Not Converge. Math. Oper. Res. Jérôme Bolte, Cyrille W. Combettes, Edouard Pauwels
2023	A*	`conf`	On the complexity of nonsmooth automatic differentiation. ICLR Jérôme Bolte, Ryan Boustany, Edouard Pauwels, Béatrice Pesquet-Popescu
2023	A*	`conf`	One-step differentiation of iterative algorithms. NeurIPS Jérôme Bolte, Edouard Pauwels, Samuel Vaiter
2023	J	`jnl`	One-step differentiation of iterative algorithms. CoRR Jérôme Bolte, Edouard Pauwels, Samuel Vaiter
2023	J	`jnl`	Subgradient Sampling for Nonsmooth Nonconvex Minimization. SIAM J. Optim. Jérôme Bolte, Tam Le, Edouard Pauwels
2023	J	`jnl`	The Derivatives of Sinkhorn-Knopp Converge. SIAM J. Optim. Edouard Pauwels, Samuel Vaiter
2023	J	`jnl`	The backtrack Hölder gradient method with application to min-max and min-min problems. Open J. Math. Optim. Jérôme Bolte, Lilian Glaudin, Edouard Pauwels, Mathieu Serrurier
2022	J	`jnl`	A sublevel moment-SOS hierarchy for polynomial optimization. Comput. Optim. Appl. Tong Chen, Jean-Bernard Lasserre, Victor Magron, Edouard Pauwels
2022	A*	`conf`	Automatic differentiation of nonsmooth iterative algorithms. NeurIPS Jérôme Bolte, Edouard Pauwels, Samuel Vaiter
2022	J	`jnl`	Automatic differentiation of nonsmooth iterative algorithms. CoRR Jérôme Bolte, Edouard Pauwels, Samuel Vaiter
2022	J	`jnl`	Curiosities and counterexamples in smooth convex optimization. Math. Program. Jérôme Bolte, Edouard Pauwels
2022	J	`jnl`	Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems. CoRR Jérôme Bolte, Edouard Pauwels, Antonio José Silveti-Falls
2022	J	`jnl`	Nonsmooth automatic differentiation: a cheap gradient principle and other complexity results. CoRR Jérôme Bolte, Ryan Boustany, Edouard Pauwels, Béatrice Pesquet-Popescu
2022	J	`jnl`	Path differentiability of ODE flows. CoRR Swann Marx, Edouard Pauwels
2022	J	`jnl`	Second-Order Step-Size Tuning of SGD for Non-Convex Optimization. Neural Process. Lett. Camille Castera, Jérôme Bolte, Cédric Févotte, Edouard Pauwels
2021	J	`jnl`	An Inertial Newton Algorithm for Deep Learning. J. Mach. Learn. Res. Camille Castera, Jérôme Bolte, Cédric Févotte, Edouard Pauwels
2021	J	`jnl`	Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning. Math. Program. Jérôme Bolte, Edouard Pauwels
2021	J	`jnl`	Data Analysis from Empirical Moments and the Christoffel Function. Found. Comput. Math. Edouard Pauwels, Mihai Putinar, Jean-Bernard Lasserre
2021	J	`jnl`	Incremental Without Replacement Sampling in Nonconvex Optimization. J. Optim. Theory Appl. Edouard Pauwels
2021	J	`jnl`	Nonsmooth Implicit Differentiation for Machine Learning and Optimization. CoRR Jérôme Bolte, Tam Le, Edouard Pauwels, Antonio Silveti-Falls
2021	A*	`conf`	Nonsmooth Implicit Differentiation for Machine-Learning and Optimization. NeurIPS Jérôme Bolte, Tam Le, Edouard Pauwels, Antonio Silveti-Falls
2021	A*	`conf`	Numerical influence of ReLU'(0) on backpropagation. NeurIPS David Bertoin, Jérôme Bolte, Sébastien Gerchinovitz, Edouard Pauwels
2021	J	`jnl`	Numerical influence of ReLU'(0) on backpropagation. CoRR David Bertoin, Jérôme Bolte, Sébastien Gerchinovitz, Edouard Pauwels
2021	J	`jnl`	Second-order step-size tuning of SGD for non-convex optimization. CoRR Camille Castera, Jérôme Bolte, Cédric Févotte, Edouard Pauwels
2021	A*	`conf`	Semialgebraic Representation of Monotone Deep Equilibrium Models and Applications to Certification. NeurIPS Tong Chen, Jean B. Lasserre, Victor Magron, Edouard Pauwels
2021	J	`jnl`	Sequential convergence of AdaGrad algorithm for smooth convex optimization. Oper. Res. Lett. Cheik Traoré, Edouard Pauwels
2020	J	`jnl`	A Hölderian backtracking method for min-max and min-min problems. CoRR Jérôme Bolte, Lilian Glaudin, Edouard Pauwels, Mathieu Serrurier
2020	A*	`conf`	A mathematical model for automatic differentiation in machine learning. NeurIPS Jérôme Bolte, Edouard Pauwels
2020	J	`jnl`	A mathematical model for automatic differentiation in machine learning. CoRR Jérôme Bolte, Edouard Pauwels
2020	J	`jnl`	Incremental Without Replacement Sampling in Nonconvex Optimization. CoRR Edouard Pauwels
2020	J	`jnl`	Long term dynamics of the subgradient method for Lipschitz path differentiable functions. CoRR Jérôme Bolte, Edouard Pauwels, Rodolfo Rios-Zertuche
2020	J	`jnl`	Polynomial Optimization for Bounding Lipschitz Constants of Deep Networks. CoRR Tong Chen, Jean-Bernard Lasserre, Victor Magron, Edouard Pauwels
2020	A*	`conf`	Semialgebraic Optimization for Lipschitz Constants of ReLU Networks. NeurIPS Tong Chen, Jean B. Lasserre, Victor Magron, Edouard Pauwels
2020	J	`jnl`	Sequential convergence of AdaGrad algorithm for smooth convex optimization. CoRR Cheik Traoré, Edouard Pauwels
2020	J	`jnl`	The multiproximal linearization method for convex composite problems. Math. Program. Jérôme Bolte, Zheng Chen, Edouard Pauwels
2019	J	`jnl`	An Inertial Newton Algorithm for Deep Learning. CoRR Camille Castera, Jérôme Bolte, Cédric Févotte, Edouard Pauwels
2019	J	`jnl`	Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning. CoRR Jérôme Bolte, Edouard Pauwels
2019	J	`jnl`	Rate of convergence for geometric inference based on the empirical Christoffel function. CoRR Mai Trang Vu, François Bachoc, Edouard Pauwels
2019	J	`jnl`	The empirical Christoffel function with applications in data analysis. Adv. Comput. Math. Jean B. Lasserre, Edouard Pauwels
2018	J	`jnl`	Extragradient Method in Optimization: Convergence and Complexity. J. Optim. Theory Appl. Trong Phong Nguyen, Edouard Pauwels, Emile Richard, Bruce W. Suter
2018	J	`jnl`	On Fienup Methods for Sparse Phase Retrieval. IEEE Trans. Signal Process. Edouard Pauwels, Amir Beck, Yonina C. Eldar, Shoham Sabach
2018	J	`jnl`	Primal and dual predicted decrease approximation methods. Math. Program. Amir Beck, Edouard Pauwels, Shoham Sabach
2018	J	`jnl`	Qualification Conditions in Semialgebraic Programming. SIAM J. Optim. Jérôme Bolte, Antoine Hochart, Edouard Pauwels
2018	A*	`conf`	Relating Leverage Scores and Density using Regularized Christoffel Functions. NeurIPS Edouard Pauwels, Francis R. Bach, Jean-Philippe Vert
2018	J	`jnl`	Relating Leverage Scores and Density using Regularized Christoffel Functions. CoRR Edouard Pauwels, Francis R. Bach, Jean-Philippe Vert
2017	J	`jnl`	On Fienup Methods for Regularized Phase Retrieval. CoRR Edouard Pauwels, Amir Beck, Yonina C. Eldar, Shoham Sabach
2017	—	`ch.`	Positivity Certificates in Optimal Control. Geometric and Numerical Foundations of Movements Edouard Pauwels, Didier Henrion, Jean-Bernard Lasserre
2017	J	`jnl`	The empirical Christoffel function in Statistics and Machine Learning. CoRR Jean-Bernard Lasserre, Edouard Pauwels
2016	J	`jnl`	Linear Conic Optimization for Inverse Optimal Control. SIAM J. Control. Optim. Edouard Pauwels, Didier Henrion, Jean-Bernard Lasserre
2016	J	`jnl`	Majorization-Minimization Procedures and Convergence of SQP Methods for Semi-Algebraic and Tame Programs. Math. Oper. Res. Jérôme Bolte, Edouard Pauwels
2016	—	`conf`	Sorting out typicality with the inverse moment matrix SOS polynomial. NIPS Edouard Pauwels, Jean B. Lasserre
2016	J	`jnl`	Sorting out typicality with the inverse moment matrix SOS polynomial. CoRR Jean-Bernard Lasserre, Edouard Pauwels
2016	J	`jnl`	The value function approach to convergence analysis in composite optimization. Oper. Res. Lett. Edouard Pauwels
2015	J	`jnl`	The Cyclic Block Conditional Gradient Method for Convex Optimization Problems. SIAM J. Optim. Amir Beck, Edouard Pauwels, Shoham Sabach
2014	J	`jnl`	A Bayesian active learning strategy for sequential experimental design in systems biology. BMC Syst. Biol. Edouard Pauwels, Christian Lajaunie, Jean-Philippe Vert
2014	—	`conf`	Inverse optimal control with polynomial optimization. CDC Edouard Pauwels, Didier Henrion, Jean-Bernard Lasserre
2014	J	`jnl`	Inverse optimal control with polynomial optimization. CoRR Edouard Pauwels, Didier Henrion, Jean-Bernard Lasserre
2012	J	`jnl`	Drug Side-Effect Prediction Based on the Integration of Chemical and Biological Spaces. J. Chem. Inf. Model. Yoshihiro Yamanishi, Edouard Pauwels, Masaaki Kotera
2012	J	`jnl`	Identification of chemogenomic features from drug-target interaction networks using interpretable classifiers. Bioinform. Yasuo Tabei, Edouard Pauwels, Véronique Stoven, Kazuhiro Takemoto, Yoshihiro Yamanishi
2012	J	`jnl`	Relating drug-protein interaction network with drug side effects. Bioinform. Sayaka Mizutani, Edouard Pauwels, Véronique Stoven, Susumu Goto, Yoshihiro Yamanishi
2011	J	`jnl`	Extracting Sets of Chemical Substructures and Protein Domains Governing Drug-Target Interactions. J. Chem. Inf. Model. Yoshihiro Yamanishi, Edouard Pauwels, Hiroto Saigo, Véronique Stoven
2011	J	`jnl`	Predicting drug side-effect profiles: a chemical fragment-based approach. BMC Bioinform. Edouard Pauwels, Véronique Stoven, Yoshihiro Yamanishi

Nicolò Altamura is a security engineer and computer science researcher specializing in software protection, reverse engineering, program analysis, and binary deobfuscation. He holds a master's degree in Computer Science and Engineering from the University of Verona, graduating with honors, and works at emproof, focusing on software protection and the challenges of analyzing and understanding compiled software.

His research explores the relationship between program analysis and code obfuscation, with particular emphasis on how software transformations affect the ability of automated tools to recover program behavior. His interests span static analysis, binary analysis, decompilation, reverse engineering, and techniques for analyzing and simplifying obfuscated code.

Beyond academic research, Nicolò develops and contributes to tools for reverse engineering and software analysis. His projects include obfuscation_analysis, a Binary Ninja plugin for analyzing and simplifying obfuscated code; Pocket, an obfuscator for mixed Boolean-arithmetic expressions; and ptxNinja, a tool for reverse engineering NVIDIA GPU code represented in the PTX virtual instruction set.

His research also extends to binary datasets and software evolution. In 2026, he co-authored ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage, a research work addressing the availability of binary data across multiple software builds and points in time, supporting research into binary analysis and changes between program versions.

Across his research, engineering work, and open-source contributions, Nicolò focuses on advancing the understanding, analysis, and protection of software against increasingly sophisticated obfuscation and reverse-engineering challenges.

Nicolò Altamura is not a football player. Please avoid reporting this kind of infromation.