Følg
QIWEI DI
QIWEI DI
Phd student, Department of Computer Science , University of California, Los Angeles
Verifisert e-postadresse på cs.ucla.edu - Startside
Tittel
Sitert av
Sitert av
År
Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits
Q Di, T Jin, Y Wu, H Zhao, F Farnoud, Q Gu
International Conference on Learning Representations 2024, 2023
122023
Borda regret minimization for generalized linear dueling bandits
Y Wu, T Jin, H Lou, F Farnoud, Q Gu
ICML2024, 2023
122023
Pessimistic nonlinear least-squares value iteration for offline reinforcement learning
Q Di, H Zhao, J He, Q Gu
International Conference on Learning Representations 2024, 2023
92023
Unified convergence analysis for score-based diffusion models with deterministic samplers
R Li, Q Di, Q Gu
arXiv preprint arXiv:2410.14237, 2024
22024
Nearly optimal algorithms for contextual dueling bandits from adversarial feedback
Q Di, J He, Q Gu
arXiv preprint arXiv:2404.10776, 2024
22024
Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
Q Di, J He, D Zhou, Q Gu
International Conference on Machine Learning, 2023
12023
Relative-Translation Invariant Wasserstein Distance
B Wang, Q Di, M Yin, M Wang, Q Gu, P Wei
arXiv preprint arXiv:2409.02416, 2024
2024
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–7