29 citations · 137 across the 11 of their papers we have counts for
8 papers · 1 filter
Style Miner: Find Significant and Stable Explanatory Factors in Time Series with Constrained Reinforcement Learning
Dapeng Li, Feiyang Pan, Jia He +3
In high-dimensional time-series analysis, it is essential to have a set of key factors (namely, the style factors) that explain the change of the observed variable. For example, vo…
Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback
Haoming Li, Feiyang Pan, Xiang Ao +6
The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few…
GuideBoot: Guided Bootstrap for Deep Contextual Bandits
Feiyang Pan, Haoming Li, Xiang Ao +4
The exploration/exploitation (E&E) dilemma lies at the core of interactive systems such as online advertising, for which contextual bandit algorithms have been proposed. Bayesian a…
Trust the Model When It Is Confident: Masked Model-based Actor-Critic
Feiyang Pan, Jia He, Dandan Tu +1
It is a popular belief that model-based Reinforcement Learning (RL) is more sample efficient than model-free RL, but in practice, it is not always true due to overweighed model err…
Field-aware Calibration: A Simple and Empirically Strong Method for Reliable Probabilistic Predictions
Feiyang Pan, Xiang Ao, Pingzhong Tang +4
It is often observed that the probabilistic predictions given by a machine learning model can disagree with averaged actual outcomes on specific subsets of data, which is also know…
Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings
Feiyang Pan, Shuokai Li, Xiang Ao +2
Click-through rate (CTR) prediction has been one of the most central problems in computational advertising. Lately, embedding techniques that produce low-dimensional representation…
Policy Optimization with Model-based Explorations
Feiyang Pan, Qingpeng Cai, An-Xiang Zeng +5
Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games…
Policy Gradients for Contextual Recommendations
Feiyang Pan, Qingpeng Cai, Pingzhong Tang +2
Decision making is a challenging task in online recommender systems. The decision maker often needs to choose a contextual item at each step from a set of candidates. Contextual ba…