Massimiliano Pontil

A Bregman Proximal Viewpoint on Neural Operators ICML 2025 An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications AISTATS 2025 Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups ICML 2025 Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues ICLR 2025 Consistent Long-Term Forecasting of Ergodic Dynamical Systems ICML 2024 From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach NeurIPS 2024 Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm JMLR 2024 Learning invariant representations of time-homogeneous stochastic dynamical systems ICLR 2024 Learning the Infinitesimal Generator of Stochastic Diffusion Processes NeurIPS 2024 Neural Conditional Probability for Uncertainty Quantification NeurIPS 2024 Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates ICML 2024 Operator World Models for Reinforcement Learning NeurIPS 2024 Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start JMLR 2023 Estimating Koopman operators with sketching to provably learn large scale dynamical systems NeurIPS 2023 Multi-task Representation Learning with Stochastic Linear Bandits AISTATS 2023 Sharp Spectral Rates for Koopman Operator Learning NeurIPS 2023 Transfer learning for atomistic simulations using GNNs and kernel mean embeddings NeurIPS 2023 A gradient estimator via L1-randomization for online zero-order optimization with two point feedback NeurIPS 2022 Batch Greenkhorn Algorithm for Entropic-Regularized Multimarginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity ICML 2022 Bregman Neural Networks ICML 2022 Conditional Meta-Learning of Linear Representations NeurIPS 2022 Distribution Regression with Sliced Wasserstein Kernels ICML 2022 Group Meritocratic Fairness in Linear Contextual Bandits NeurIPS 2022 Implicit kernel meta-learning using kernel integral forms UAI 2022 Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces NeurIPS 2022 Multi-source domain adaptation via weighted joint distributions optimal transport UAI 2022 A Gang of Adversarial Bandits NeurIPS 2021 Best Model Identification: A Rested Bandit Formulation ICML 2021 Concentration inequalities under sub-Gaussian and sub-exponential conditions NeurIPS 2021 Convergence Properties of Stochastic Hypergradients AISTATS 2021 Distance-Based Regularisation of Deep Networks for Fine-Tuning ICLR 2021 Distributed Zero-Order Optimization under Adversarial Noise NeurIPS 2021 Multi-task and meta-learning with sparse linear bandits UAI 2021 Robust Unsupervised Learning via L-statistic Minimization ICML 2021 The Role of Global Labels in Few-Shot Classification and How to Infer Them NeurIPS 2021 Estimating weighted areas under the ROC curve NeurIPS 2020 Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits NeurIPS 2020 Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning NeurIPS 2020 Fair regression via plug-in estimator and recalibration with statistical guarantees NeurIPS 2020 Fair regression with Wasserstein barycenters NeurIPS 2020 Marthe: Scheduling the Learning Rate Via Online Hypergradients IJCAI 2020 Meta-learning with Stochastic Linear Bandits ICML 2020 Online Parameter-Free Learning of Multiple Low Variance Tasks UAI 2020 On the Iteration Complexity of Hypergradient Computation ICML 2020 The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning NeurIPS 2020 Learning Discrete Structures for Graph Neural Networks ICML 2019 Learning-to-Learn Stochastic Gradient Descent with Biased Regularization ICML 2019 Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification NeurIPS 2019 Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction ICML 2019 Online-Within-Online Meta-Learning NeurIPS 2019 Sinkhorn Barycenters with Free Support via Frank-Wolfe Algorithm NeurIPS 2019 Uniform concentration and symmetrization for weak interactions COLT 2019 Bilevel learning of the Group Lasso structure NeurIPS 2018 Bilevel Programming for Hyperparameter Optimization and Meta-Learning ICML 2018 Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance NeurIPS 2018 Empirical bounds for functions with weak interactions COLT 2018 Empirical Risk Minimization Under Fairness Constraints NeurIPS 2018 Learning To Learn Around A Common Mean NeurIPS 2018 A Speaker Adaptive DNN Training Approach for Speaker-Independent Acoustic Inversion Interspeech 2017 Consistent Multitask Learning with Nonlinear Output Relations NeurIPS 2017 Forward and Reverse Gradient-Based Hyperparameter Optimization ICML 2017 Regret Bounds for Lifelong Learning AISTATS 2017 Fitting Spectral Decay with the k-Support Norm AISTATS 2016 Mistake Bounds for Binary Matrix Completion NeurIPS 2016 New Perspectives on k-Support and Cluster Norms JMLR 2016 The Benefit of Multitask Representation Learning JMLR 2016 Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification CVPR 2016 Learning With Dataset Bias in Latent Subcategory Models CVPR 2015 Predicting a Switching Sequence of Graph Labelings JMLR 2015 An Inequality with Applications to Structured Sparsity and Multitask Dictionary Learning COLT 2014 Spectral k-Support Norm Regularization NeurIPS 2014 A New Convex Relaxation for Tensor Completion NeurIPS 2013 Excess risk bounds for multitask learning with trace norm regularization COLT 2013 Multilinear Multitask Learning ICML 2013 A General Framework for Structured Sparsity via Proximal Optimization AISTATS 2012 Exploiting Unrelated Tasks in Multi-Task Learning AISTATS 2012 Optimal kernel choice for large-scale two-sample tests NeurIPS 2012 Structured Sparsity and Generalization JMLR 2012 A Family of Penalty Functions for Structured Sparsity NeurIPS 2010 On Spectral Learning JMLR 2010 When Is There a Representer Theorem? Vector Versus Matrix Regularizers JMLR 2009 Fast Prediction on a Tree NeurIPS 2008 Online Prediction on Large Diameter Graphs NeurIPS 2008 Universal Multi-Task Kernels JMLR 2008 A Spectral Regularization Framework for Multi-Task Structure Learning NeurIPS 2007 Multi-Task Feature Learning NeurIPS 2006 Prediction on a Graph with a Perceptron NeurIPS 2006 Learning Multiple Tasks with Kernel Methods JMLR 2005 Learning the Kernel Function via Regularization JMLR 2005 Stability of Randomized Learning Algorithms JMLR 2005