Francis Bach

Optimal Denoising in Score-Based Generative Models: The Role of Data Regularity JMLR 2025 Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation JMLR 2025 Enhanced Feature Learning via Regularisation: Integrating Neural Networks and Kernel Methods JMLR 2025 Efficient Optimization Algorithms for Linear Adversarial Training AISTATS 2025 Variational Inference on the Boolean Hypercube with the Quantum Entropy AISTATS 2025 An uncertainty principle for Linear Recurrent Neural Networks COLT 2025 The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training ICML 2025 Physics-informed Kernel Learning JMLR 2025 Geometry-Dependent Matching Pursuit: a Transition Phase for Convergence on Linear Regression and LASSO JMLR 2025 Statistical Collusion by Collectives on Learning Platforms ICML 2025 Sampling Binary Data by Denoising through Score Functions ICML 2025 Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence NIPS 2024 Classifier Calibration with ROC-Regularized Isotonic Regression AISTATS 2024 Chain of Log-Concave Markov Chains ICLR 2024 Physics-informed machine learning as a kernel method COLT 2024 The Galerkin method beats Graph-Based Approaches for Spectral Algorithms AISTATS 2024 On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions AISTATS 2024 Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy ICML 2023 On Bridging the Gap between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization ICML 2023 Kernelized Diffusion Maps COLT 2023 Regression as Classification: Influence of Task Formulation on Neural Network Features AISTATS 2023 Explicit Regularization in Overparametrized Models via Noise Injection AISTATS 2023 Sampling from Arbitrary Functions via PSD Models AISTATS 2022 Convergence of Uncertainty Sampling for Active Learning ICML 2022 On the Consistency of Max-Margin Losses AISTATS 2022 Anticorrelated Noise Injection for Improved Generalization ICML 2022 Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of Squares COLT 2022 Deep Equals Shallow for ReLU Networks in Kernel Regimes ICLR 2021 Fast Rates for Structured Prediction COLT 2021 A Dimension-free Computational Upper-bound for Smooth Optimal Transport Estimation COLT 2021 Disambiguation of Weak Supervision leading to Exponential Convergence rates ICML 2021 Explicit Regularization of Stochastic Gradient Methods through Duality AISTATS 2021 Learning With Subquadratic Regularization : A Primal-Dual Approach IJCAI 2020 Statistical Estimation of the Poincaré constant and Application to Sampling Multimodal Distributions AISTATS 2020 Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss COLT 2020 Consistent Structured Prediction with Max-Min Margin Markov Networks ICML 2020 Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization ICML 2020 Structured Prediction with Partial Labelling through the Infimum Loss ICML 2020 Stochastic Optimization for Regularized Wasserstein Estimators ICML 2020 Stochastic algorithms with descent guarantees for ICA AISTATS 2019 Sample Complexity of Sinkhorn Divergences AISTATS 2019 Sharp Analysis of Learning with Discrete Losses AISTATS 2019 Overcomplete Independent Component Analysis via SDP AISTATS 2019 Unsupervised Image Matching and Object Discovery as Optimization CVPR 2019 UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization NIPS 2019 Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses NIPS 2019 An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums NIPS 2019 Localized Structured Prediction NIPS 2019 Optimal Convergence Rates for Convex Distributed Optimization in Networks JMLR 2019 Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions COLT 2019 Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance COLT 2019 A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise COLT 2019 Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks NIPS 2019 Massively scalable Sinkhorn distances via the Nyström method NIPS 2019 Fast Decomposable Submodular Function Minimization using Constrained Total Variation NIPS 2019 Towards closing the gap between the theory and practice of SVRG NIPS 2019 On Lazy Training in Differentiable Programming NIPS 2019 Partially Encrypted Deep Learning using Functional Encryption NIPS 2019 Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives AISTATS 2019 Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron AISTATS 2019 Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes NIPS 2018 Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes NIPS 2018 SING: Symbol-to-Instrument Neural Generator NIPS 2018 Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization NIPS 2018 Optimal Algorithms for Non-Smooth Distributed Optimization in Networks NIPS 2018 On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport NIPS 2018 Relating Leverage Scores and Density using Regularized Christoffel Functions NIPS 2018 Learning Determinantal Point Processes in Sublinear Time AISTATS 2018 Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods AISTATS 2018 Convex Optimization over Intersection of Simple Sets: improved Convergence Rate Guarantees via an Exact Penalty Approach AISTATS 2018 A Generic Approach for Escaping Saddle points AISTATS 2018 Combinatorial Penalties: Which structures are preserved by convex relaxations? AISTATS 2018 Exponential Convergence of Testing Error for Stochastic Gradient Methods COLT 2018 Averaging Stochastic Gradient Descent on Riemannian Manifolds COLT 2018 Integration Methods and Optimization Algorithms NIPS 2017 A Quantitative Measure of the Impact of Coarticulation on Phone Discriminability INTERSPEECH 2017 Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks ICML 2017 Identifying Groups of Strongly Correlated Variables through Smoothed Ordered Weighted $L_1$-norms AISTATS 2017 Active-set Methods for Submodular Minimization Problems JMLR 2017 Kernel Square-Loss Exemplar Machines for Image Retrieval CVPR 2017 Nonlinear Acceleration of Stochastic Algorithms NIPS 2017 On Structured Prediction Theory with Calibrated Convex Surrogate Losses NIPS 2017 Online but Accurate Inference for Latent Variable Models with Local Gibbs Sampling JMLR 2017 Stochastic Composite Least-Squares Regression with Convergence Rate $O(1/n)$ COLT 2017 Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression JMLR 2017 Robust Discriminative Clustering with Sparse Regularizers JMLR 2017 On the Consistency of Ordinal Regression Methods JMLR 2017 On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions JMLR 2017 Breaking the Curse of Dimensionality with Convex Neural Networks JMLR 2017 Parameter Learning for Log-supermodular Distributions NIPS 2016 Regularized Nonlinear Acceleration NIPS 2016 PAC-Bayesian Theory Meets Bayesian Inference NIPS 2016 Highly-Smooth Zero-th Order Online Optimization COLT 2016 Stochastic Variance Reduction Methods for Saddle-Point Problems NIPS 2016 Stochastic Optimization for Large-scale Optimal Transport NIPS 2016 Beyond CCA: Moment Matching for Multi-View Models ICML 2016 Weakly-Supervised Alignment of Video With Text ICCV 2015 From Averaging to Acceleration, There is Only a Step-size COLT 2015 Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering AISTATS 2015 Averaged Least-Mean-Squares: Bias-Variance Trade-offs and Optimal Sampling Distributions AISTATS 2015 Rethinking LDA: Moment Matching for Discrete ICA NIPS 2015 Spectral Norm Regularization of Orthonormal Representations for Graph Transduction NIPS 2015 Adaptivity of Averaged Stochastic Gradient Descent to Local Strong Convexity for Logistic Regression JMLR 2014 Metric Learning for Temporal Sequence Alignment NIPS 2014 SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives NIPS 2014 A Markovian approach to distributional semantics with application to semantic compositionality COLING 2014 Large-Margin Metric Learning for Constrained Partitioning Problems ICML 2014 Convex Relaxations for Learning Bounded-Treewidth Decomposable Graphs ICML 2013 Intersecting singularities for multi-structured estimation ICML 2013 Learning Sparse Penalties for Change-point Detection using Max Margin Interval Regression ICML 2013 Sharp analysis of low-rank kernel matrix approximations COLT 2013 Structured Penalties for Log-Linear Language Models EMNLP 2013 Hidden Markov tree models for semantic class induction CONLL 2013 Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n) NIPS 2013 Convex Relaxations for Permutation Problems NIPS 2013 Reflection methods for user-friendly submodular optimization NIPS 2013 Multi-task Regression using Minimal Penalties JMLR 2012 Convex and Network Flow Optimization for Structured Sparsity JMLR 2011 Structured Variable Selection with Sparsity-Inducing Norms JMLR 2011 Proximal Methods for Hierarchical Sparse Coding JMLR 2011 Online Learning for Matrix Factorization and Sparse Coding JMLR 2010 Structured Sparse Principal Component Analysis AISTATS 2010 A New Approach to Collaborative Filtering: Operator Estimation with Spectral Regularization JMLR 2009 Optimal Solutions for Sparse Principal Component Analysis JMLR 2008