4 papers
Right, Wrong, or Unfinished: A Competing Risks Framework for Language-Model Reasoning under Token Budgets
Boen Jiang, Guanhua Fang, Wen Yu
Assessing language-model performance under a token budget requires understanding both when a response will finish and whether it will be correct. We develop Competing Risks Analysi…
Learning under Commission and Omission Event Outliers
Yuecheng Zhang, Guanhua Fang, Wen Yu
Event stream is an important data format in real life. The events are usually expected to follow some regular patterns over time. However, the patterns could be contaminated by une…
On Non-asymptotic Theory of Recurrent Neural Networks in Temporal Point Processes
Zhiheng Chen, Guanhua Fang, Wen Yu
Temporal point process (TPP) is an important tool for modeling and predicting irregularly timed events across various domains. Recently, the recurrent neural network (RNN)-based TP…
On Robust Clustering of Temporal Point Process
Yuecheng Zhang, Guanhua Fang, Wen Yu
Clustering of event stream data is of great importance in many application scenarios, including but not limited to, e-commerce, electronic health, online testing, mobile music serv…