Publications

2022

• Chloé Rouyer, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Yevgeny Seldin. A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs. NeurIPS, 2022. [arXiv]

• Saeed Masoudian, Julian Zimmert, Yevgeny Seldin. A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback. NeurIPS 2022. [arXiv]

• Yi-Shan Wu, Yevgeny Seldin. Split-kl and PAC-Bayes-split-kl Inequalities. NeurIPS, 2022. [arXiv]

• Nikolaos Nomikos, Mohammad Sadegh Talebi, Themistoklis Charalambous, Risto Wichman. Bandit-based power control in full-duplex cooperative relay networks with strict-sense stationary and non-stationary wireless communication channels. IEEE Open Journal of the Communications Society 3: 366-378, 2022. [doi]

2021

• Mohammad Sadegh Talebi, Anders Jonsson, Odalric Maillard. Improved Exploration in Factored Average-Reward MDPs. AISTATS, 2021. [paper]

• Yi-Shan Wu, Yevgeny Seldin, Andres R Masegosa, Christian Igel, Stephan Sloth Lorenzen. Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote. NeurIPS, 2021. [paper]

• Yi-Shan Wu, Yi-Te Hong, Chi-Jen Lu. Lifelong Learning with Branching Experts. ACML, 2021. [paper]

• Chloé Rouyer, Yevgeny Seldin, and Nicolò Cesa-Bianchi. An algorithm for stochastic and adversarial bandits with switching costs. ICML, 2021. [arXiv]

• Yijie Zhang and Herke van Hoof. Deep coherent exploration for continuous control. ICML, 2021. [paper]

• Saeed Masoudian and Yevgeny Seldin. Improved analysis of robustness of the Tsallis-INF algorithm to adversarial corruptions in stochastic multiarmed bandits. COLT, 2021. [arXiv]