On the Efficient Marginalization of Probabilistic Sequence Models
This work addresses the challenge of handling long-range probabilistic queries in sequential data for fields such as medicine and finance, representing an incremental advancement by extending existing autoregressive models with tailored approximation methods.
The paper tackles the problem of efficiently answering complex probabilistic queries beyond single-step prediction in sequential models, developing novel approximation techniques for marginalization that are model-agnostic and applicable to various domains like discrete sequences and point processes.
Real-world data often exhibits sequential dependence, across diverse domains such as human behavior, medicine, finance, and climate modeling. Probabilistic methods capture the inherent uncertainty associated with prediction in these contexts, with autoregressive models being especially prominent. This dissertation focuses on using autoregressive models to answer complex probabilistic queries that go beyond single-step prediction, such as the timing of future events or the likelihood of a specific event occurring before another. In particular, we develop a broad class of novel and efficient approximation techniques for marginalization in sequential models that are model-agnostic. These techniques rely solely on access to and sampling from next-step conditional distributions of a pre-trained autoregressive model, including both traditional parametric models as well as more recent neural autoregressive models. Specific approaches are presented for discrete sequential models, for marked temporal point processes, and for stochastic jump processes, each tailored to a well-defined class of informative, long-range probabilistic queries.