Publications
Publications
Preprints and reports, then 65 peer-reviewed papers (26 at NeurIPS), most recent first. The same record is on DBLP and Google Scholar; preprints are on arXiv.
Preprints and reports · 2026 · 2025 · 2024 · 2023 · 2022 · 2021 · 2020 · 2019 · 2018 · 2017 · 2016 · 2015 · 2014 · 2013 · 2012 · 2011 · 2010
Preprints and reports
- Proof-Carrying Contracts: Commitments AI Agents Cannot BreakCarlo Ciliberto, Alessandro Rudi and Enrico TassiarXiv:2610.28484, 2026 · program · website · code
- Privacy-Preserving LLM Inference in Practice: A Comparative Survey of Techniques, Trade-Offs, and DeployabilityDavide Andreoletti, Alessandro Rudi, Emanuele Carpanzano, Francesco Lelli and Tiziano LeidiCryptology ePrint Archive, report 2026/105, 2026
2026
- Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal AlgorithmPierre Boudart, Pierre Gaillard and Alessandro RudiALT, 2026 · arXiv
- Non-parametric Learning of Stochastic Differential Equations with Non-asymptotic Fast Rates of ConvergenceRiccardo Bonalli and Alessandro RudiFoundations of Computational Mathematics, 2026 · arXiv
2025
- Dynamic Regret Reduces to Kernelized Static RegretAndrew Jacobsen, Alessandro Rudi, Francesco Orabona and Nicolò Cesa-BianchiNeurIPS, 2025 · arXiv
- Safely Learning Controlled Stochastic DynamicsLuc Brogat-Motte, Alessandro Rudi and Riccardo BonalliNeurIPS, 2025 · arXiv
- Approximation of optimization problems with constraints through kernel Sum-of-SquaresPierre-Cyril Aubin-Frankowski and Alessandro RudiOptimization, 2025 · arXiv
- Finding global minima via kernel approximationsAlessandro Rudi, Ulysse Marteau-Ferey and Francis R. BachMathematical Programming, 2025 · arXiv
- Solving Moment and Polynomial Optimization Problems on Sobolev SpacesDidier Henrion and Alessandro RudiSIAM Journal on Optimization, 2025 · arXiv
2024
- Optimal Estimation of Smooth Transport Maps with Kernel SoSAdrien Vacher, Boris Muzellec, Francis R. Bach, François-Xavier Vialard and Alessandro RudiSIAM Journal on Mathematics of Data Science, 2024 · arXiv
- Second Order Conditions to Decompose Smooth Functions as Sums of SquaresUlysse Marteau-Ferey, Francis R. Bach and Alessandro RudiSIAM Journal on Optimization, 2024 · arXiv
2023
- Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite ModelsAnant Raj, Umut Simsekli and Alessandro RudiNeurIPS, 2023 · arXiv
- GloptiNets: Scalable Non-Convex Optimization with CertificatesGaspard Beugnot, Julien Mairal and Alessandro RudiNeurIPS, 2023 Spotlight · arXiv
- Exponential Convergence of Sum-of-Squares Hierarchies for Trigonometric PolynomialsFrancis R. Bach and Alessandro RudiSIAM Journal on Optimization, 2023 · arXiv
2022
- Active Labeling: Streaming Stochastic GradientsVivien Cabannes, Francis R. Bach, Vianney Perchet and Alessandro RudiNeurIPS, 2022 · arXiv
- Infinite-Dimensional Sums-of-Squares for Optimal ControlEloïse Berthier, Justin Carpentier, Alessandro Rudi and Francis R. BachIEEE CDC, 2022 · arXiv
- Measuring dissimilarity with diffeomorphism invarianceThéophile Cantelobre, Carlo Ciliberto, Benjamin Guedj and Alessandro RudiICML, 2022 · arXiv
- Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of SquaresBlake E. Woodworth, Francis R. Bach and Alessandro RudiCOLT, 2022 · arXiv
- Nyström Kernel Mean EmbeddingsAntoine Chatalic, Nicolas Schreuder, Lorenzo Rosasco and Alessandro RudiICML, 2022 · arXiv
- On the Benefits of Large Learning Rates for Kernel MethodsGaspard Beugnot, Julien Mairal and Alessandro RudiCOLT, 2022 · arXiv
- On the Consistency of Max-Margin LossesAlex Nowak, Alessandro Rudi and Francis R. BachAISTATS, 2022 · arXiv
- Sampling from Arbitrary Functions via PSD ModelsUlysse Marteau-Ferey, Francis R. Bach and Alessandro RudiAISTATS, 2022 · arXiv
- Vector-Valued Least-Squares Regression under Output Regularity AssumptionsLuc Brogat-Motte, Alessandro Rudi, Céline Brouard, Juho Rousu and Florence d'Alché-BucJournal of Machine Learning Research, 2022 · arXiv
2021
- Beyond Tikhonov: faster learning with self-concordant losses, via iterative regularizationGaspard Beugnot, Julien Mairal and Alessandro RudiNeurIPS, 2021 Spotlight · arXiv
- Mixability made efficient: Fast online multiclass logistic regressionRémi Jézéquel, Pierre Gaillard and Alessandro RudiNeurIPS, 2021 Spotlight · arXiv
- Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learningVivien Cabannes, Loucas Pillaud-Vivien, Francis R. Bach and Alessandro RudiNeurIPS, 2021 · arXiv
- PSD Representations for Effective Probability ModelsAlessandro Rudi and Carlo CilibertoNeurIPS, 2021 · arXiv
- A Dimension-free Computational Upper-bound for Smooth Optimal Transport EstimationAdrien Vacher, Boris Muzellec, Alessandro Rudi, Francis R. Bach and François-Xavier VialardCOLT, 2021 · arXiv
- Disambiguation of Weak Supervision leading to Exponential Convergence ratesVivien A. Cabannes, Francis R. Bach and Alessandro RudiICML, 2021 · arXiv
- Fast Rates for Structured PredictionVivien A. Cabannes, Francis R. Bach and Alessandro RudiCOLT, 2021 · arXiv
2020
- Kernel Methods Through the Roof: Handling Billions of Points EfficientlyGiacomo Meanti, Luigi Carratino, Lorenzo Rosasco and Alessandro RudiNeurIPS, 2020 Oral · arXiv · code
- Non-parametric Models for Non-negative FunctionsUlysse Marteau-Ferey, Francis R. Bach and Alessandro RudiNeurIPS, 2020 Spotlight · arXiv
- Consistent Structured Prediction with Max-Min Margin Markov NetworksAlex Nowak, Francis R. Bach and Alessandro RudiICML, 2020 · arXiv
- Efficient improper learning for online logistic regressionRémi Jézéquel, Pierre Gaillard and Alessandro RudiCOLT, 2020 · arXiv
- Gain with no Pain: Efficiency of Kernel-PCA by Nyström SamplingNicholas Sterge, Bharath K. Sriperumbudur, Lorenzo Rosasco and Alessandro RudiAISTATS, 2020 · arXiv
- Statistical Estimation of the Poincaré constant and Application to Sampling Multimodal DistributionsLoucas Pillaud-Vivien, Francis R. Bach, Tony Lelièvre, Alessandro Rudi and Gabriel StoltzAISTATS, 2020 · arXiv
- Structured Prediction with Partial Labelling through the Infimum LossVivien Cabannes, Alessandro Rudi and Francis R. BachICML, 2020 · arXiv
- A General Framework for Consistent Structured Prediction with Implicit Loss EmbeddingsCarlo Ciliberto, Lorenzo Rosasco and Alessandro RudiJournal of Machine Learning Research, 2020 · arXiv
- Approximating Hamiltonian dynamics with the Nyström methodAlessandro Rudi, Leonard Wossnig, Carlo Ciliberto, Andrea Rocchetto, Massimiliano Pontil and Simone SeveriniQuantum, 2020 · arXiv
- Faster Kriging: Facing High-Dimensional SimulatorsXuefei Lu, Alessandro Rudi, Emanuele Borgonovo and Lorenzo RosascoOperations Research, 2020
- Optimal rates for spectral algorithms with least-squares regression over Hilbert spacesJunhong Lin, Alessandro Rudi, Lorenzo Rosasco and Volkan CevherApplied and Computational Harmonic Analysis, 2020 · arXiv
- Statistical limits of supervised quantum learningCarlo Ciliberto, Andrea Rocchetto, Alessandro Rudi and Leonard WossnigPhysical Review A, 2020 · arXiv
2019
- Efficient online learning with kernels for adversarial large scale problemsRémi Jézéquel, Pierre Gaillard and Alessandro RudiNeurIPS, 2019 · arXiv
- Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant LossesUlysse Marteau-Ferey, Francis R. Bach and Alessandro RudiNeurIPS, 2019 · arXiv
- Localized Structured PredictionCarlo Ciliberto, Francis R. Bach and Alessandro RudiNeurIPS, 2019 · arXiv
- Massively scalable Sinkhorn distances via the Nyström methodJason M. Altschuler, Francis R. Bach, Alessandro Rudi and Jonathan Niles-WeedNeurIPS, 2019 · arXiv
- Affine Invariant Covariance Estimation for Heavy-Tailed DistributionsDmitrii M. Ostrovskii and Alessandro RudiCOLT, 2019 · arXiv
- Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-ConcordanceUlysse Marteau-Ferey, Dmitrii Ostrovskii, Francis R. Bach and Alessandro RudiCOLT, 2019 · arXiv
- Sharp Analysis of Learning with Discrete LossesAlex Nowak-Vila, Francis R. Bach and Alessandro RudiAISTATS, 2019 · arXiv
2018
- Differential Properties of Sinkhorn Approximation for Learning with Wasserstein DistanceGiulia Luise, Alessandro Rudi, Massimiliano Pontil and Carlo CilibertoNeurIPS, 2018 · arXiv
- Learning with SGD and Random FeaturesLuigi Carratino, Alessandro Rudi and Lorenzo RosascoNeurIPS, 2018 Spotlight · arXiv
- Manifold Structured PredictionAlessandro Rudi, Carlo Ciliberto, Gian Maria Marconi and Lorenzo RosascoNeurIPS, 2018 · arXiv
- On Fast Leverage Score Sampling and Optimal LearningAlessandro Rudi, Daniele Calandriello, Luigi Carratino and Lorenzo RosascoNeurIPS, 2018 · arXiv
- Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple PassesLoucas Pillaud-Vivien, Alessandro Rudi and Francis R. BachNeurIPS, 2018 · arXiv
- Exponential Convergence of Testing Error for Stochastic Gradient MethodsLoucas Pillaud-Vivien, Alessandro Rudi and Francis R. BachCOLT, 2018 · arXiv
2017
- Consistent Multitask Learning with Nonlinear Output RelationsCarlo Ciliberto, Alessandro Rudi, Lorenzo Rosasco and Massimiliano PontilNeurIPS, 2017 · arXiv
- FALKON: An Optimal Large Scale Kernel MethodAlessandro Rudi, Luigi Carratino and Lorenzo RosascoNeurIPS, 2017 · arXiv · code · slides
- Generalization Properties of Learning with Random FeaturesAlessandro Rudi and Lorenzo RosascoNeurIPS, 2017 Oral · arXiv · slides
- Regularized Kernel Algorithms for Support EstimationAlessandro Rudi, Ernesto De Vito, Alessandro Verri and Francesca OdoneFrontiers in Applied Mathematics and Statistics, 2017
2016
- A Consistent Regularization Approach for Structured PredictionCarlo Ciliberto, Lorenzo Rosasco and Alessandro RudiNeurIPS, 2016 · arXiv · slides
- NYTRO: When Subsampling Meets Early StoppingRaffaello Camoriano, Tomás Angles, Alessandro Rudi and Lorenzo RosascoAISTATS, 2016 · arXiv
2015
- Less is More: Nyström Computational RegularizationAlessandro Rudi, Raffaello Camoriano and Lorenzo RosascoNeurIPS, 2015 Oral · arXiv · slides
2014
- Geometrical and computational aspects of Spectral Support Estimation for novelty detectionAlessandro Rudi, Francesca Odone and Ernesto De VitoPattern Recognition Letters, 2014
2013
- On the Sample Complexity of Subspace LearningAlessandro Rudi, Guillermo D. Cañas and Lorenzo RosascoNeurIPS, 2013 · arXiv
2012
- Adaptive Optimization for Cross ValidationAlessandro Rudi, Gabriele Chiusano and Alessandro VerriESANN, 2012
2011
- A general method for the point of regard estimation in 3D spaceFiora Pirri, Matia Pizzoli and Alessandro RudiCVPR, 2011
2010
- Linear Solvability in the Viewing GraphAlessandro Rudi, Matia Pizzoli and Fiora PirriACCV, 2010