Francesco Orabona

Cards Against Contamination: TCG-Bench for Difficulty-Scalable Multilingual LLM Reasoning EACL 2026 New Lower Bounds for Non-Convex Stochastic Optimization through Divergence Decomposition COLT 2025 ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning ICML 2025 Square$χ$PO: Differentially Private and Robust $χ^2$-Preference Optimization in Offline Direct Alignment ICML 2025 Self-Directed Node Classification on Graphs ALT 2025 A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO ICML 2025 An Equivalence Between Static and Dynamic Regret Minimization NIPS 2024 Better-than-KL PAC-Bayes Bounds COLT 2024 Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion ICLR 2024 Algorithmic Learning Theory 2023: Preface ALT 2023 Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion ICML 2023 Generalized Implicit Follow-The-Regularized-Leader ICML 2023 Tighter PAC-Bayes Bounds Through Coin-Betting COLT 2023 On the Initialization for Convex-Concave Min-max Problems ALT 2022 Robustness to Unbounded Smoothness of Generalized SignSGD NIPS 2022 Better Parameter-Free Stochastic Optimization with ODE Updates for Coin-Betting AAAI 2022 Implicit Parameter-free Online Learning with Truncated Linear Models ALT 2022 On the Last Iterate Convergence of Momentum Methods ALT 2022 A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance ICML 2021 Online Learning with Optimism and Delay ICML 2021 Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers NIPS 2021 Temporal Variability in Implicit Online Learning NIPS 2020 On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes AISTATS 2019 Momentum-Based Variance Reduction in Non-Convex SGD NIPS 2019 Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration NIPS 2019 Parameter-Free Online Convex Optimization with Sub-Exponential Noise COLT 2019 Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization ICML 2019 Black-Box Reductions for Parameter-free Online Learning in Banach Spaces COLT 2018 Efficient Online Bandit Multiclass Learning with $\tilde{O}(\sqrt{T})$ Regret ICML 2017 Training Deep Networks without Learning Rates Through Coin Betting NIPS 2017 Improved Strongly Adaptive Online Learning using Coin Betting AISTATS 2017 Open Problem: Parameter-Free and Scale-Free Online Algorithms COLT 2016 Solving Ridge Regression using Sketched Preconditioned SVRG ICML 2016 Parameter-Free Convex Learning through Coin Betting AUTOML 2016 Coin Betting and Parameter-Free Online Learning NIPS 2016 On Measure Concentration of Random Maximum A-Posteriori Perturbations ICML 2014 Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations COLT 2014 On Multilabel Classification and Ranking with Bandit Feedback JMLR 2014 Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning NIPS 2014 From N to N+1: Multiclass Transfer Incremental Learning CVPR 2013 Multiclass Latent Locally Linear Support Vector Machines ACML 2013 Stability and Hypothesis Transfer Learning ICML 2013 Dimension-Free Exponentiated Gradient NIPS 2013 Regression-tree Tuning in a Streaming Setting NIPS 2013 On Multilabel Classification and Ranking with Partial Feedback NIPS 2012 Multi Kernel Learning with Online-Batch Optimization JMLR 2012 Beyond Logarithmic Bounds in Online Learning AISTATS 2012 Learning from Candidate Labeling Sets NIPS 2010 New Adaptive Algorithms for Online Classification NIPS 2010 Bounded Kernel-Based Online Learning JMLR 2009