default search action
Francesco Orabona
Person information
- affiliation: King Abdullah University of Science and Technology, Saudi Arabia
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j16]Francesco Orabona, Kwang-Sung Jun:
Tight Concentrations and Confidence Sequences From the Regret of Universal Portfolio. IEEE Trans. Inf. Theory 70(1): 436-455 (2024) - [c66]Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona:
Better-than-KL PAC-Bayes Bounds. COLT 2024: 3325-3352 - [c65]Alexandru Meterez, Amir Joudaki, Francesco Orabona, Alexander Immer, Gunnar Rätsch, Hadi Daneshmand:
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion. ICLR 2024 - [i52]Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona:
Better-than-KL PAC-Bayes Bounds. CoRR abs/2402.09201 (2024) - [i51]Andrew Jacobsen, Francesco Orabona:
An Equivalence Between Static and Dynamic Regret Minimization. CoRR abs/2406.01577 (2024) - [i50]Georgy Sokolov, Maximilian Thiessen, Margarita Akhmejanova, Fabio Vitale, Francesco Orabona:
Self-Directed Learning of Convex Labelings on Graphs. CoRR abs/2409.01428 (2024) - 2023
- [c64]Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona:
Tighter PAC-Bayes Bounds Through Coin-Betting. COLT 2023: 2240-2264 - [c63]Keyi Chen, Francesco Orabona:
Generalized Implicit Follow-The-Regularized-Leader. ICML 2023: 4826-4838 - [c62]Ashok Cutkosky, Harsh Mehta, Francesco Orabona:
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. ICML 2023: 6643-6670 - [e1]Shipra Agrawal, Francesco Orabona:
International Conference on Algorithmic Learning Theory, February 20-23, 2023, Singapore. Proceedings of Machine Learning Research 201, PMLR 2023 [contents] - [i49]Ashok Cutkosky, Harsh Mehta, Francesco Orabona:
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. CoRR abs/2302.03775 (2023) - [i48]Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona:
Tighter PAC-Bayes Bounds Through Coin-Betting. CoRR abs/2302.05829 (2023) - [i47]Keyi Chen, Francesco Orabona:
Generalized Implicit Follow-The-Regularized-Leader. CoRR abs/2306.00201 (2023) - [i46]Keyi Chen, Francesco Orabona:
Implicit Interpretation of Importance Weight Aware Updates. CoRR abs/2307.11955 (2023) - [i45]Francesco Orabona:
Normalized Gradients for All. CoRR abs/2308.05621 (2023) - [i44]Alexandru Meterez, Amir Joudaki, Francesco Orabona, Alexander Immer, Gunnar Rätsch, Hadi Daneshmand:
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion. CoRR abs/2310.02012 (2023) - 2022
- [j15]Zhenxun Zhuang, Mingrui Liu, Ashok Cutkosky, Francesco Orabona:
Understanding AdamW through Proximal Methods and Scale-Freeness. Trans. Mach. Learn. Res. 2022 (2022) - [c61]Keyi Chen, John Langford, Francesco Orabona:
Better Parameter-Free Stochastic Optimization with ODE Updates for Coin-Betting. AAAI 2022: 6239-6247 - [c60]Keyi Chen, Ashok Cutkosky, Francesco Orabona:
Implicit Parameter-free Online Learning with Truncated Linear Models. ALT 2022: 148-175 - [c59]Xiaoyu Li, Mingrui Liu, Francesco Orabona:
On the Last Iterate Convergence of Momentum Methods. ALT 2022: 699-717 - [c58]Mingrui Liu, Francesco Orabona:
On the Initialization for Convex-Concave Min-max Problems. ALT 2022: 743-767 - [c57]Michael Crawshaw, Mingrui Liu, Francesco Orabona, Wei Zhang, Zhenxun Zhuang:
Robustness to Unbounded Smoothness of Generalized SignSGD. NeurIPS 2022 - [i43]Zhenxun Zhuang, Mingrui Liu, Ashok Cutkosky, Francesco Orabona:
Understanding AdamW through Proximal Methods and Scale-Freeness. CoRR abs/2202.00089 (2022) - [i42]Keyi Chen, Ashok Cutkosky, Francesco Orabona:
Implicit Parameter-free Online Learning with Truncated Linear Models. CoRR abs/2203.10327 (2022) - [i41]Michael Crawshaw, Mingrui Liu, Francesco Orabona, Wei Zhang, Zhenxun Zhuang:
Robustness to Unbounded Smoothness of Generalized SignSGD. CoRR abs/2208.11195 (2022) - 2021
- [c56]Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey:
Online Learning with Optimism and Delay. ICML 2021: 3363-3373 - [c55]Xiaoyu Li, Zhenxun Zhuang, Francesco Orabona:
A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance. ICML 2021: 6553-6564 - [c54]Jeffrey Negrea, Blair L. Bilodeau, Nicolò Campolongo, Francesco Orabona, Daniel M. Roy:
Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers. NeurIPS 2021: 26237-26249 - [i40]Francesco Orabona, Dávid Pál:
Parameter-free Stochastic Optimization of Variationally Coherent Functions. CoRR abs/2102.00236 (2021) - [i39]Xiaoyu Li, Mingrui Liu, Francesco Orabona:
On the Last Iterate Convergence of Momentum Methods. CoRR abs/2102.07002 (2021) - [i38]Nicolò Campolongo, Francesco Orabona:
A closer look at temporal variability in dynamic online learning. CoRR abs/2102.07666 (2021) - [i37]Mingrui Liu, Francesco Orabona:
A Parameter-free Algorithm for Convex-concave Min-max Problems. CoRR abs/2103.00284 (2021) - [i36]Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey:
Online Learning with Optimism and Delay. CoRR abs/2106.06885 (2021) - [i35]Francesco Orabona, Kwang-Sung Jun:
Tight Concentrations and Confidence Sequences from the Regret of Universal Portfolio. CoRR abs/2110.14099 (2021) - [i34]Jeffrey Negrea, Blair L. Bilodeau, Nicolò Campolongo, Francesco Orabona, Daniel M. Roy:
Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers. CoRR abs/2110.14804 (2021) - 2020
- [c53]Nicolò Campolongo, Francesco Orabona:
Temporal Variability in Implicit Online Learning. NeurIPS 2020 - [i33]Xiaoyu Li, Zhenxun Zhuang, Francesco Orabona:
Exponential Step Sizes for Non-Convex Optimization. CoRR abs/2002.05273 (2020) - [i32]Nicolò Campolongo, Francesco Orabona:
Temporal Variability in Implicit Online Learning. CoRR abs/2006.07503 (2020) - [i31]Keyi Chen, John Langford, Francesco Orabona:
Better Parameter-free Stochastic Optimization with ODE Updates for Coin-Betting. CoRR abs/2006.07507 (2020) - [i30]Xiaoyu Li, Francesco Orabona:
A High Probability Analysis of Adaptive SGD with Momentum. CoRR abs/2007.14294 (2020) - [i29]Mingrui Liu, Wei Zhang, Francesco Orabona, Tianbao Yang:
Adam+: A Stochastic Method with Adaptive Variance Reduction. CoRR abs/2011.11985 (2020)
2010 – 2019
- 2019
- [j14]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): 6539-6560 (2019) - [c52]Xiaoyu Li, Francesco Orabona:
On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes. AISTATS 2019: 983-992 - [c51]Kwang-Sung Jun, Francesco Orabona:
Parameter-Free Online Convex Optimization with Sub-Exponential Noise. COLT 2019: 1802-1823 - [c50]Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona:
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization. ICML 2019: 7664-7672 - [c49]Ashok Cutkosky, Francesco Orabona:
Momentum-Based Variance Reduction in Non-Convex SGD. NeurIPS 2019: 15210-15219 - [c48]Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona:
Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. NeurIPS 2019: 15332-15341 - [i28]Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona:
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization. CoRR abs/1901.09068 (2019) - [i27]Kwang-Sung Jun, Francesco Orabona:
Parameter-free Online Convex Optimization with Sub-Exponential Noise. CoRR abs/1902.01500 (2019) - [i26]Ashok Cutkosky, Francesco Orabona:
Momentum-Based Variance Reduction in Non-Convex SGD. CoRR abs/1905.10018 (2019) - [i25]Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona:
Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. CoRR abs/1905.10680 (2019) - [i24]Kwang-Sung Jun, Francesco Orabona:
Parameter-Free Locally Differentially Private Stochastic Subgradient Descent. CoRR abs/1911.09564 (2019) - [i23]Francesco Orabona:
A Modern Introduction to Online Learning. CoRR abs/1912.13213 (2019) - 2018
- [j13]Francesco Orabona, Dávid Pál:
Scale-free online learning. Theor. Comput. Sci. 716: 50-69 (2018) - [c47]Ashok Cutkosky, Francesco Orabona:
Black-Box Reductions for Parameter-free Online Learning in Banach Spaces. COLT 2018: 1493-1529 - [i22]Ashok Cutkosky, Francesco Orabona:
Black-Box Reductions for Parameter-free Online Learning in Banach Spaces. CoRR abs/1802.06293 (2018) - [i21]Xiaoyu Li, Francesco Orabona:
On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes. CoRR abs/1805.08114 (2018) - 2017
- [j12]Ilja Kuzborskij, Francesco Orabona, Barbara Caputo:
Scalable greedy algorithms for transfer learning. Comput. Vis. Image Underst. 156: 174-185 (2017) - [j11]Ilja Kuzborskij, Francesco Orabona:
Fast rates by transferring from auxiliary hypotheses. Mach. Learn. 106(2): 171-195 (2017) - [c46]Kwang-Sung Jun, Francesco Orabona, Stephen J. Wright, Rebecca Willett:
Improved Strongly Adaptive Online Learning using Coin Betting. AISTATS 2017: 943-951 - [c45]Alina Beygelzimer, Francesco Orabona, Chicheng Zhang:
Efficient Online Bandit Multiclass Learning with Õ(√T) Regret. ICML 2017: 488-497 - [c44]Francesco Orabona, Tatiana Tommasi:
Training Deep Networks without Learning Rates Through Coin Betting. NIPS 2017: 2160-2170 - [i20]Alina Beygelzimer, Francesco Orabona, Chicheng Zhang:
Efficient Online Bandit Multiclass Learning with $\tilde{O}(\sqrt{T})$ Regret. CoRR abs/1702.07958 (2017) - [i19]Francesco Orabona, Tatiana Tommasi:
Backprop without Learning Rates Through Coin Betting. CoRR abs/1705.07795 (2017) - [i18]Kwang-Sung Jun, Francesco Orabona, Stephen J. Wright, Rebecca Willett:
Online Learning for Changing Environments using Coin Betting. CoRR abs/1711.02545 (2017) - 2016
- [c43]Francesco Orabona, Dávid Pál:
Open Problem: Parameter-Free and Scale-Free Online Algorithms. COLT 2016: 1659-1664 - [c42]Francesco Orabona, Dávid Pál:
Parameter-Free Convex Learning through Coin Betting. AutoML@ICML 2016: 75-82 - [c41]Alon Gonen, Francesco Orabona, Shai Shalev-Shwartz:
Solving Ridge Regression using Sketched Preconditioned SVRG. ICML 2016: 1397-1405 - [c40]Francesco Orabona, Dávid Pál:
Coin Betting and Parameter-Free Online Learning. NIPS 2016: 577-585 - [i17]Francesco Orabona, Dávid Pál:
Scale-Free Online Learning. CoRR abs/1601.01974 (2016) - [i16]Alon Gonen, Francesco Orabona, Shai Shalev-Shwartz:
Solving Ridge Regression using Sketched Preconditioned SVRG. CoRR abs/1602.02350 (2016) - [i15]Tamir Hazan, Francesco Orabona, Anand D. Sarwate, Subhransu Maji, Tommi S. Jaakkola:
High Dimensional Inference with Random Maximum A-Posteriori Perturbations. CoRR abs/1602.03571 (2016) - [i14]Francesco Orabona, Dávid Pál:
From Coin Betting to Parameter-Free Online Learning. CoRR abs/1602.04128 (2016) - [i13]Kwang-Sung Jun, Francesco Orabona, Rebecca Willett, Stephen J. Wright:
Improved Strongly Adaptive Online Learning using Coin Betting. CoRR abs/1610.04578 (2016) - 2015
- [j10]Francesco Orabona, Koby Crammer, Nicolò Cesa-Bianchi:
A generalized online mirror descent with applications to classification and regression. Mach. Learn. 99(3): 411-435 (2015) - [c39]Francesco Orabona, Dávid Pál:
Scale-Free Algorithms for Online Linear Optimization. ALT 2015: 287-301 - [c38]Rocco De Rosa, Francesco Orabona, Nicolò Cesa-Bianchi:
The ABACOC Algorithm: A Novel Approach for Nonparametric Classification of Data Streams. ICDM 2015: 733-738 - [c37]Ilja Kuzborskij, Francesco Orabona, Barbara Caputo:
Transfer Learning Through Greedy Subset Selection. ICIAP (1) 2015: 3-14 - [i12]Francesco Orabona:
A Simple Expression for Mill's Ratio of the Student's t-Distribution. CoRR abs/1502.01632 (2015) - [i11]Francesco Orabona, Dávid Pál:
Scale-Free Algorithms for Online Linear Optimization. CoRR abs/1502.05744 (2015) - [i10]Rocco De Rosa, Francesco Orabona, Nicolò Cesa-Bianchi:
The ABACOC Algorithm: a Novel Approach for Nonparametric Classification of Data Streams. CoRR abs/1508.04912 (2015) - [i9]Francesco Orabona, Dávid Pál:
Optimal Non-Asymptotic Lower Bound on the Minimax Regret of Learning with Expert Advice. CoRR abs/1511.02176 (2015) - 2014
- [j9]Claudio Gentile, Francesco Orabona:
On multilabel classification and ranking with bandit feedback. J. Mach. Learn. Res. 15(1): 2451-2487 (2014) - [j8]Tatiana Tommasi, Francesco Orabona, Barbara Caputo:
Learning Categories From Few Examples With Multi Model Knowledge Transfer. IEEE Trans. Pattern Anal. Mach. Intell. 36(5): 928-941 (2014) - [c36]H. Brendan McMahan, Francesco Orabona:
Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations. COLT 2014: 1020-1039 - [c35]Francesco Orabona, Tamir Hazan, Anand D. Sarwate, Tommi S. Jaakkola:
On Measure Concentration of Random Maximum A-Posteriori Perturbations. ICML 2014: 432-440 - [c34]Francesco Orabona:
Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning. NIPS 2014: 1116-1124 - [i8]H. Brendan McMahan, Francesco Orabona:
Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations. CoRR abs/1403.0628 (2014) - [i7]Francesco Orabona:
Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning. CoRR abs/1406.3816 (2014) - [i6]Ilja Kuzborskij, Barbara Caputo, Francesco Orabona:
Transfer Learning through Greedy Subset Selection. CoRR abs/1408.1292 (2014) - [i5]Ilja Kuzborskij, Francesco Orabona:
Learning by Transferring from Auxiliary Hypotheses. CoRR abs/1412.1619 (2014) - 2013
- [j7]Tatiana Tommasi, Francesco Orabona, Claudio Castellini, Barbara Caputo:
Improving Control of Dexterous Hand Prostheses Using Adaptive Learning. IEEE Trans. Robotics 29(1): 207-219 (2013) - [c33]Marco Fornoni, Barbara Caputo, Francesco Orabona:
Multiclass Latent Locally Linear Support Vector Machines. ACML 2013: 229-244 - [c32]Ilja Kuzborskij, Francesco Orabona, Barbara Caputo:
From N to N+1: Multiclass Transfer Incremental Learning. CVPR 2013: 3358-3365 - [c31]Ilja Kuzborskij, Francesco Orabona:
Stability and Hypothesis Transfer Learning. ICML (3) 2013: 942-950 - [c30]Samory Kpotufe, Francesco Orabona:
Regression-tree Tuning in a Streaming Setting. NIPS 2013: 1788-1796 - [c29]Francesco Orabona:
Dimension-Free Exponentiated Gradient. NIPS 2013: 1806-1814 - [i4]Francesco Orabona, Koby Crammer, Nicolò Cesa-Bianchi:
A Generalized Online Mirror Descent with Applications to Classification and Regression. CoRR abs/1304.2994 (2013) - [i3]Francesco Orabona, Tamir Hazan, Anand D. Sarwate, Tommi S. Jaakkola:
On Measure Concentration of Random Maximum A-Posteriori Perturbations. CoRR abs/1310.4227 (2013) - 2012
- [j6]Francesco Orabona, Jie Luo, Barbara Caputo:
Multi Kernel Learning with Online-Batch Optimization. J. Mach. Learn. Res. 13: 227-253 (2012) - [c28]Tatiana Tommasi, Francesco Orabona, Mohsen Kaboli, Barbara Caputo:
Leveraging over prior knowledge for online learning of visual categories. BMVC 2012: 1-11 - [c27]Claudio Gentile, Francesco Orabona:
On Multilabel Classification and Ranking with Partial Feedback. NIPS 2012: 1160-1168 - [c26]Francesco Orabona, Nicolò Cesa-Bianchi, Claudio Gentile:
Beyond Logarithmic Bounds in Online Learning. AISTATS 2012: 823-831 - [i2]Francesco Orabona, Andreas Argyriou, Nathan Srebro:
PRISMA: PRoximal Iterative SMoothing Algorithm. CoRR abs/1206.2372 (2012) - [i1]Claudio Gentile, Francesco Orabona:
On Multilabel Classification and Ranking with Partial Feedback. CoRR abs/1207.0166 (2012) - 2011
- [c25]Francesco Orabona, Jie Luo:
Ultra-Fast Optimization Algorithm for Sparse Multi Kernel Learning. ICML 2011: 249-256 - [c24]Francesco Orabona, Nicolò Cesa-Bianchi:
Better Algorithms for Selective Sampling. ICML 2011: 433-440 - 2010
- [j5]Etienne Grossmann, José António Gaspar, Francesco Orabona:
Discrete camera calibration from pixel streams. Comput. Vis. Image Underst. 114(2): 198-209 (2010) - [j4]Francesco Orabona, Claudio Castellini, Barbara Caputo, Jie Luo, Giulio Sandini:
On-line independent support vector machines. Pattern Recognit. 43(4): 1402-1412 (2010) - [c23]Francesco Orabona, Marco Fornoni, Barbara Caputo, Nicolò Cesa-Bianchi:
OM-2: An online multi-class Multi-Kernel Learning algorithm Luo Jie. CVPR Workshops 2010: 43-50 - [c22]Francesco Orabona, Jie Luo, Barbara Caputo:
Online-batch strongly convex Multi Kernel Learning. CVPR 2010: 787-794 - [c21]Tatiana Tommasi, Francesco Orabona, Barbara Caputo:
Safety in numbers: Learning categories from few examples with multi model knowledge transfer. CVPR 2010: 3081-3088 - [c20]Jie Luo, Francesco Orabona:
Learning from Candidate Labeling Sets. NIPS 2010: 1504-1512 - [c19]Francesco Orabona, Koby Crammer:
New Adaptive Algorithms for Online Classification. NIPS 2010: 1840-1848 - [p1]Tatiana Tommasi, Francesco Orabona:
Idiap on Medical Image Classification. ImageCLEF 2010: 453-465
2000 – 2009
- 2009
- [j3]Francesco Orabona, Joseph Keshet, Barbara Caputo:
Bounded Kernel-Based Online Learning. J. Mach. Learn. Res. 10: 2643-2666 (2009) - [c18]Jie Luo, Francesco Orabona, Barbara Caputo:
An Online Framework for Learning Novel Concepts over Multiple Cues. ACCV (1) 2009: 269-280 - [c17]Nicolò Cesa-Bianchi, Claudio Gentile, Francesco Orabona:
Robust bounds for classification via selective sampling. ICML 2009: 121-128 - [c16]Francesco Orabona, Claudio Castellini, Barbara Caputo, Angelo Emanuele Fiorilla, Giulio Sandini:
Model adaptation with least-squares SVM for adaptive hand prosthetics. ICRA 2009: 2897-2903 - [c15]Muhammad Muneeb Ullah, Francesco Orabona, Barbara Caputo:
You live, you learn, you forget: Continuous learning of visual places with a forgetting mechanism. IROS 2009: 3154-3161 - 2008
- [j2]Tatiana Tommasi, Francesco Orabona, Barbara Caputo:
Discriminative cue integration for medical image annotation. Pattern Recognit. Lett. 29(15): 1996-2002 (2008) - [c14]Tatiana Tommasi, Francesco Orabona, Barbara Caputo:
An SVM Confidence-Based Approach to Medical Image Annotation. CLEF 2008: 696-703 - [c13]Tatiana Tommasi, Francesco Orabona, Barbara Caputo:
CLEF2008 Image Annotation Task: an SVM Confidence-Based Approach. CLEF (Working Notes) 2008 - [c12]Etienne Grossmann, José António Gaspar, Francesco Orabona: