Filtrer vos résultats
- 35
- 1
- 20
- 13
- 2
- 1
- 1
- 31
- 24
- 22
- 2
- 2
- 1
- 2
- 4
- 4
- 6
- 6
- 4
- 1
- 2
- 3
- 2
- 1
- 1
- 35
- 1
- 19
- 17
- 17
- 6
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 36
- 5
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
36 résultats
|
|
triés par
|
|
A Chaining Algorithm for Online Nonparametric RegressionCOLT 2015, Jul 2015, Paris, France. pp.764-796
Communication dans un congrès
hal-01120813v2
|
||
|
Online Sign Identification: Minimization of the Number of Errors in Thresholding BanditsNeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Virtual, Canada. pp.1-25
Communication dans un congrès
hal-03363014v1
|
||
|
Efficient Kernel UCB for Contextual BanditsInternational Conference on Artificial Intelligence and Statistics, Mar 2022, Valencia, Spain. pp.5689-5720
Communication dans un congrès
hal-03575953v1
|
||
|
Target Tracking for Contextual Bandits: Application to Demand Side ManagementThirty-sixth International Conference on Machine Learning, Jun 2019, Long Beach, United States. pp.754-763
Communication dans un congrès
hal-01994144v2
|
||
|
Efficient improper learning for online logistic regressionCOLT 2020 - 33rd Annual Conference on Learning Theory, Jul 2020, Graz / Virtual, Austria
Communication dans un congrès
hal-02510505v3
|
||
|
Dueling Bandits with Adversarial SleepingNeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Virtual, Canada. pp.1-25
Communication dans un congrès
hal-03451845v1
|
||
|
Online Learning Approach for Survival Analysis2024
Pré-publication, Document de travail
hal-04418099v1
|
||
|
Experimental Comparison of Semi-parametric, Parametric, and Machine Learning Models for Time-to-Event Analysis Through the Concordance Index2020
Pré-publication, Document de travail
hal-02507132v1
|
||
|
Accelerated Gossip in Networks of Given Dimension using Jacobi Polynomial Iterations2019
Pré-publication, Document de travail
hal-01797016v2
|
||
|
Mirror Descent Meets Fixed Share (and feels no regret)NIPS 2012, Dec 2012, Lake Tahoe, United States. Paper 471
Communication dans un congrès
hal-00670514v2
|
||
|
Efficient and Near-Optimal Online Portfolio Selection2022
Pré-publication, Document de travail
hal-03787674v1
|
||
|
Mixability made efficient: Fast online multiclass logistic regressionNeurIPS 2021. Thirty-fifth Conference on Neural Information Processing Systems, Dec 2021, Online, France
Communication dans un congrès
hal-03370530v1
|
||
|
A consistent deterministic regression tree for non-parametric prediction of time series2014
Pré-publication, Document de travail
hal-00987803v2
|
||
|
Sparse Accelerated Exponential Weights20th International Conference on Artificial Intelligence and Statistics (AISTATS), Apr 2017, Fort Lauderdale, United States
Communication dans un congrès
hal-01376808v1
|
||
|
Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent2023
Pré-publication, Document de travail
hal-04302000v1
|
||
|
Experimental Comparison of Semi-parametric, Parametric, and Machine Learning Methods for Time-to-Event Analysis Through the IPEC ScoreSFdS 2020 - 52èmes Journées de Statistiques de la Société Française de Statistique, Jun 2021, Nice, France. pp.1-6
Communication dans un congrès
hal-03221512v1
|
||
|
Sequential Counterfactual Risk MinimizationICML 2023 - 40th International Conference on Machine Learning, Jul 2023, Honololu, Hawaii, United States. pp.1-26
Communication dans un congrès
hal-04106246v1
|
||
|
Online Learning and Game Theory. A quick overview with recent results and applicationsESAIM: Proceedings, 2015, 51, pp.246 - 271. ⟨10.1051/proc/201551014⟩
Article dans une revue
hal-01237039v1
|
||
|
Covariance-Adaptive Least-Squares Algorithm for Stochastic Combinatorial Semi-Bandits2024
Pré-publication, Document de travail
hal-04470568v1
|
||
|
Forecasting electricity consumption by aggregating specialized expertsMachine Learning, 2013, 90 (2), pp.231-260. ⟨10.1007/s10994-012-5314-7⟩
Article dans une revue
hal-00484940v3
|
||
|
A Continuized View on Nesterov Acceleration2021
Pré-publication, Document de travail
hal-03138823v1
|
||
|
Improved sleeping bandits with stochastic action sets and adversarial rewardsICML 2020 - International Conference on Machine Learning, Jul 2020, Vienna, Austria
Communication dans un congrès
hal-02950106v1
|
||
|
Uniform regret bounds over $R^d$ for the sequential linear regression problem with the square lossThe 30th International Conference on Algorithmic Learning Theory (ALT 2019), Mar 2019, Chicago, United States. pp.404-432
Communication dans un congrès
hal-01802004v2
|
||
|
Non-stationary Online Regression2020
Pré-publication, Document de travail
hal-02998781v1
|
||
|
Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from PreferencesICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore (MA), United States. pp.1-25
Communication dans un congrès
hal-03922380v1
|
||
|
A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized GossipNeurIPS 2021 - 35th Conference on Neural Information Processing Systems, Dec 2021, Sydney (virtual), Australia. pp.1-32
Communication dans un congrès
hal-03405165v1
|
||
|
Efficient online algorithms for fast-rate regret bounds under sparsityNIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, Dec 2018, Montreal, France
Communication dans un congrès
hal-01798201v1
|
||
|
(Online) Convex Optimization for Demand-Side Management: Application to Thermostatically Controlled Loads2023
Pré-publication, Document de travail
hal-03972660v3
|
||
|
Efficient online learning with kernels for adversarial large scale problems2019
Pré-publication, Document de travail
hal-02019402v2
|
||
|
Contributions à l’agrégation séquentielle robuste d’experts : Travaux sur l’erreur d’approximation et la prévision en loi. Applications à la prévision pour les marchés de l’énergie.Machine Learning [stat.ML]. Université Paris Sud - Paris XI, 2015. Français. ⟨NNT : 2015PA112133⟩
Thèse
tel-01250027v1
|
- 1
- 2