Publications

You can also find my articles on my Google Scholar profile

Preprints

B. Tasdighi, N. Werge, Y.-S. Wu, and M. Kandemir (2024). Exploring Pessimism and Optimism Dynamics in Deep Reinforcement Learning. arXiv.
B. Tasdighi, N. Werge, Y.-S. Wu, and M. Kandemir (2024). Probabilistic Actor-Critic: Learning to Explore with PAC-Bayes Uncertainty. arXiv.
A. Godichon-Baggioni and N. Werge (2023). On Adaptive Stochastic Optimization for Streaming Data: A Newton’s Method with O(dN) Operations. arXiv.
A. Dutta, E. H. Bergou, S. Boucherouite, N. Werge, M. Kandemir, and X. Li (2023). Demystifying the Myths and Legends of Nonconvex Convergence of SGD. arXiv.
N. Werge, A. Akgül, and M. Kandemir (2023). BOF-UCB: A Bayesian-Optimistic Frequentist Algorithm for Non-Stationary Contextual Bandits. arXiv.

J. de Vilmarest and N. Werge (2024). An adaptive volatility method for probabilistic forecasting and its application to the M6 financial forecasting competition. International Journal of Forecasting (IJF). arXiv. publisher link.
A. Godichon-Baggioni, N. Werge, and O. Wintenberger (2023). Learning from time-dependent streaming data with online stochastic algorithms. Transactions on Machine Learning Research (TMLR). arXiv. HAL. publisher link.
A. Godichon-Baggioni, N. Werge, and O. Wintenberger (2023). Non-asymptotic analysis of stochastic approximation algorithms for streaming data. ESAIM: Probability and Statistics 27, 482-514. arXiv. HAL. publisher link.
N. Werge and O. Wintenberger (2022). AdaVol: an adaptive recursive volatility prediction method. Econometrics and Statistics 23, 19-35. arXiv. HAL. publisher link. code.
- A note on its use in the M6 financial forecasting competition can be found on arXiv.
N. Werge (2021). Predicting risk-adjusted returns using an asset independent regime-switching model. Expert Systems with Applications 184, 115576. arXiv. HAL. publisher link.