Francesco Orabona

ORCID

Publication Activity (10 Years)

Years Active: 2005-2024
Publications (10 Years): 72

Top Venues

Publications

Alexandru Meterez, Amir Joudaki, Francesco Orabona, Alexander Immer, Gunnar Rätsch, Hadi Daneshmand
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion. ICLR (2024)
Francesco Orabona, Kwang-Sung Jun
Tight Concentrations and Confidence Sequences From the Regret of Universal Portfolio. IEEE Trans. Inf. Theory 70 (1) (2024)
Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona
Better-than-KL PAC-Bayes Bounds. COLT (2024)
Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona
Better-than-KL PAC-Bayes Bounds. CoRR (2024)
Andrew Jacobsen, Francesco Orabona
An Equivalence Between Static and Dynamic Regret Minimization. CoRR (2024)
Francesco Orabona
Normalized Gradients for All. CoRR (2023)
Alexandru Meterez, Amir Joudaki, Francesco Orabona, Alexander Immer, Gunnar Rätsch, Hadi Daneshmand
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion. CoRR (2023)
Ashok Cutkosky, Harsh Mehta, Francesco Orabona
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. ICML (2023)
Keyi Chen, Francesco Orabona
Generalized Implicit Follow-The-Regularized-Leader. ICML (2023)
Keyi Chen, Francesco Orabona
Implicit Interpretation of Importance Weight Aware Updates. CoRR (2023)
Ashok Cutkosky, Harsh Mehta, Francesco Orabona
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. CoRR (2023)
Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona
Tighter PAC-Bayes Bounds Through Coin-Betting. COLT (2023)
Keyi Chen, Francesco Orabona
Generalized Implicit Follow-The-Regularized-Leader. CoRR (2023)
Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona
Tighter PAC-Bayes Bounds Through Coin-Betting. CoRR (2023)
Keyi Chen, Ashok Cutkosky, Francesco Orabona
Implicit Parameter-free Online Learning with Truncated Linear Models. ALT (2022)
Xiaoyu Li, Mingrui Liu, Francesco Orabona
On the Last Iterate Convergence of Momentum Methods. ALT (2022)
Keyi Chen, Ashok Cutkosky, Francesco Orabona
Implicit Parameter-free Online Learning with Truncated Linear Models. CoRR (2022)
Michael Crawshaw, Mingrui Liu, Francesco Orabona, Wei Zhang, Zhenxun Zhuang
Robustness to Unbounded Smoothness of Generalized SignSGD. CoRR (2022)
Mingrui Liu, Francesco Orabona
On the Initialization for Convex-Concave Min-max Problems. ALT (2022)
Zhenxun Zhuang, Mingrui Liu, Ashok Cutkosky, Francesco Orabona
Understanding AdamW through Proximal Methods and Scale-Freeness. CoRR (2022)
Keyi Chen, John Langford, Francesco Orabona
Better Parameter-Free Stochastic Optimization with ODE Updates for Coin-Betting. AAAI (2022)
Michael Crawshaw, Mingrui Liu, Francesco Orabona, Wei Zhang, Zhenxun Zhuang
Robustness to Unbounded Smoothness of Generalized SignSGD. NeurIPS (2022)
Zhenxun Zhuang, Mingrui Liu, Ashok Cutkosky, Francesco Orabona
Understanding AdamW through Proximal Methods and Scale-Freeness. Trans. Mach. Learn. Res. 2022 (2022)
Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey
Online Learning with Optimism and Delay. CoRR (2021)
Jeffrey Negrea, Blair L. Bilodeau, Nicolò Campolongo, Francesco Orabona, Dan Roy
Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers. NeurIPS (2021)
Mingrui Liu, Francesco Orabona
A Parameter-free Algorithm for Convex-concave Min-max Problems. CoRR (2021)
Xiaoyu Li, Zhenxun Zhuang, Francesco Orabona
A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance. ICML (2021)
Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey
Online Learning with Optimism and Delay. ICML (2021)
Francesco Orabona, Kwang-Sung Jun
Tight Concentrations and Confidence Sequences from the Regret of Universal Portfolio. CoRR (2021)
Francesco Orabona, Dávid Pál
Parameter-free Stochastic Optimization of Variationally Coherent Functions. CoRR (2021)
Nicolò Campolongo, Francesco Orabona
A closer look at temporal variability in dynamic online learning. CoRR (2021)
Jeffrey Negrea, Blair Bilodeau, Nicolò Campolongo, Francesco Orabona, Daniel M. Roy
Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers. CoRR (2021)
Xiaoyu Li, Mingrui Liu, Francesco Orabona
On the Last Iterate Convergence of Momentum Methods. CoRR (2021)
Nicolò Campolongo, Francesco Orabona
Temporal Variability in Implicit Online Learning. NeurIPS (2020)
Nicolò Campolongo, Francesco Orabona
Temporal Variability in Implicit Online Learning. CoRR (2020)
Mingrui Liu, Wei Zhang, Francesco Orabona, Tianbao Yang
: A Stochastic Method with Adaptive Variance Reduction. CoRR (2020)
Xiaoyu Li, Francesco Orabona
A High Probability Analysis of Adaptive SGD with Momentum. CoRR (2020)
Xiaoyu Li, Zhenxun Zhuang, Francesco Orabona
Exponential Step Sizes for Non-Convex Optimization. CoRR (2020)
Keyi Chen, John Langford, Francesco Orabona
Better Parameter-free Stochastic Optimization with ODE Updates for Coin-Betting. CoRR (2020)
Francesco Orabona
A Modern Introduction to Online Learning. CoRR (2019)
Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona
Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. CoRR (2019)
Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization. ICML (2019)
Kwang-Sung Jun, Francesco Orabona
Parameter-Free Online Convex Optimization with Sub-Exponential Noise. COLT (2019)
Ashok Cutkosky, Francesco Orabona
Momentum-Based Variance Reduction in Non-Convex SGD. CoRR (2019)
Xiaoyu Li, Francesco Orabona
On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes. AISTATS (2019)
Kwang-Sung Jun, Francesco Orabona
Parameter-Free Locally Differentially Private Stochastic Subgradient Descent. CoRR (2019)
Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization. CoRR (2019)
Ashok Cutkosky, Francesco Orabona
Momentum-Based Variance Reduction in Non-Convex SGD. NeurIPS (2019)
Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona
Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. NeurIPS (2019)
Tamir Hazan, Francesco Orabona, Anand D. Sarwate, Subhransu Maji, Tommi S. Jaakkola
High Dimensional Inference With Random Maximum A-Posteriori Perturbations. IEEE Trans. Inf. Theory 65 (10) (2019)
Kwang-Sung Jun, Francesco Orabona
Parameter-free Online Convex Optimization with Sub-Exponential Noise. CoRR (2019)
Ashok Cutkosky, Francesco Orabona
Black-Box Reductions for Parameter-free Online Learning in Banach Spaces. COLT (2018)
Xiaoyu Li, Francesco Orabona
On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes. CoRR (2018)
Francesco Orabona, Dávid Pál
Scale-free online learning. Theor. Comput. Sci. 716 (2018)
Ashok Cutkosky, Francesco Orabona
Black-Box Reductions for Parameter-free Online Learning in Banach Spaces. CoRR (2018)
Alina Beygelzimer, Francesco Orabona, Chicheng Zhang
Efficient Online Bandit Multiclass Learning with $\tilde{O}(\sqrt{T})$ Regret. CoRR (2017)
Francesco Orabona, Tatiana Tommasi
Training Deep Networks without Learning Rates Through Coin Betting. NIPS (2017)
Kwang-Sung Jun, Francesco Orabona, Stephen J. Wright, Rebecca Willett
Online Learning for Changing Environments using Coin Betting. CoRR (2017)
Alina Beygelzimer, Francesco Orabona, Chicheng Zhang
Efficient Online Bandit Multiclass Learning with Õ(√T) Regret. ICML (2017)
Ilja Kuzborskij, Francesco Orabona
Fast rates by transferring from auxiliary hypotheses. Mach. Learn. 106 (2) (2017)
Francesco Orabona, Tatiana Tommasi
Backprop without Learning Rates Through Coin Betting. CoRR (2017)
Kwang-Sung Jun, Francesco Orabona, Stephen J. Wright, Rebecca Willett
Improved Strongly Adaptive Online Learning using Coin Betting. AISTATS (2017)
Ilja Kuzborskij, Francesco Orabona, Barbara Caputo
Scalable greedy algorithms for transfer learning. Comput. Vis. Image Underst. 156 (2017)
Francesco Orabona, Dávid Pál
Coin Betting and Parameter-Free Online Learning. NIPS (2016)
Francesco Orabona, Dávid Pál
From Coin Betting to Parameter-Free Online Learning. CoRR (2016)
Francesco Orabona, Dávid Pál
Scale-Free Online Learning. CoRR (2016)
Alon Gonen, Francesco Orabona, Shai Shalev-Shwartz
Solving Ridge Regression using Sketched Preconditioned SVRG. ICML (2016)
Alon Gonen, Francesco Orabona, Shai Shalev-Shwartz
Solving Ridge Regression using Sketched Preconditioned SVRG. CoRR (2016)
Tamir Hazan, Francesco Orabona, Anand D. Sarwate, Subhransu Maji, Tommi S. Jaakkola
High Dimensional Inference with Random Maximum A-Posteriori Perturbations. CoRR (2016)
Kwang-Sung Jun, Francesco Orabona, Rebecca Willett, Stephen J. Wright
Improved Strongly Adaptive Online Learning using Coin Betting. CoRR (2016)
Francesco Orabona, Dávid Pál
Open Problem: Parameter-Free and Scale-Free Online Algorithms. COLT (2016)
Francesco Orabona, Dávid Pál
Parameter-Free Convex Learning through Coin Betting. AutoML@ICML (2016)
Francesco Orabona, Dávid Pál
Scale-Free Algorithms for Online Linear Optimization. ALT (2015)
Francesco Orabona, Koby Crammer, Nicolò Cesa-Bianchi
A generalized online mirror descent with applications to classification and regression. Mach. Learn. 99 (3) (2015)
Rocco De Rosa, Francesco Orabona, Nicolò Cesa-Bianchi
The ABACOC Algorithm: A Novel Approach for Nonparametric Classification of Data Streams. ICDM (2015)
Ilja Kuzborskij, Francesco Orabona, Barbara Caputo
Transfer Learning Through Greedy Subset Selection. ICIAP (1) (2015)
Rocco De Rosa, Francesco Orabona, Nicolò Cesa-Bianchi
The ABACOC Algorithm: a Novel Approach for Nonparametric Classification of Data Streams. CoRR (2015)
Francesco Orabona
A Simple Expression for Mill's Ratio of the Student's t-Distribution. CoRR (2015)
Francesco Orabona, Dávid Pál
Scale-Free Algorithms for Online Linear Optimization. CoRR (2015)
Francesco Orabona, Dávid Pál
Optimal Non-Asymptotic Lower Bound on the Minimax Regret of Learning with Expert Advice. CoRR (2015)
H. Brendan McMahan, Francesco Orabona
Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations. CoRR (2014)
H. Brendan McMahan, Francesco Orabona
Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations. COLT (2014)
Tatiana Tommasi, Francesco Orabona, Barbara Caputo
Learning Categories From Few Examples With Multi Model Knowledge Transfer. IEEE Trans. Pattern Anal. Mach. Intell. 36 (5) (2014)
Francesco Orabona
Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning. CoRR (2014)
Francesco Orabona
Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning. NIPS (2014)
Ilja Kuzborskij, Barbara Caputo, Francesco Orabona
Transfer Learning through Greedy Subset Selection. CoRR (2014)
Ilja Kuzborskij, Francesco Orabona
Learning by Transferring from Auxiliary Hypotheses. CoRR (2014)
Francesco Orabona, Tamir Hazan, Anand D. Sarwate, Tommi S. Jaakkola
On Measure Concentration of Random Maximum A-Posteriori Perturbations. ICML (2014)
Claudio Gentile, Francesco Orabona
On multilabel classification and ranking with bandit feedback. J. Mach. Learn. Res. 15 (1) (2014)
Ilja Kuzborskij, Francesco Orabona, Barbara Caputo
From N to N+1: Multiclass Transfer Incremental Learning. CVPR (2013)
Francesco Orabona, Tamir Hazan, Anand D. Sarwate, Tommi S. Jaakkola
On Measure Concentration of Random Maximum A-Posteriori Perturbations. CoRR (2013)
Tatiana Tommasi, Francesco Orabona, Claudio Castellini, Barbara Caputo
Improving Control of Dexterous Hand Prostheses Using Adaptive Learning. IEEE Trans. Robotics 29 (1) (2013)
Samory Kpotufe, Francesco Orabona
Regression-tree Tuning in a Streaming Setting. NIPS (2013)
Marco Fornoni, Barbara Caputo, Francesco Orabona
Multiclass Latent Locally Linear Support Vector Machines. ACML (2013)
Francesco Orabona
Dimension-Free Exponentiated Gradient. NIPS (2013)
Ilja Kuzborskij, Francesco Orabona
Stability and Hypothesis Transfer Learning. ICML (3) (2013)
Francesco Orabona, Koby Crammer, Nicolò Cesa-Bianchi
A Generalized Online Mirror Descent with Applications to Classification and Regression CoRR (2013)
Tatiana Tommasi, Francesco Orabona, Mohsen Kaboli, Barbara Caputo
Leveraging over prior knowledge for online learning of visual categories. BMVC (2012)
Francesco Orabona, Nicolò Cesa-Bianchi, Claudio Gentile
Beyond Logarithmic Bounds in Online Learning. AISTATS (2012)
Claudio Gentile, Francesco Orabona
On Multilabel Classification and Ranking with Partial Feedback CoRR (2012)

Francesco Orabona.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Francesco Orabona