Divergence-Based Motivation for Online EM and Combining Hidden Variable Models
원문 초록
Expectation-Maximization (EM) is a prominent approach for parameter estimation of hidden (aka latent) variable models. Given the full batch of data, EM forms an upper-bound of the negative log-likelihood of the model at each iteration and updates to the minimizer of this upper-bound. We first provide a "model level" interpretation of the EM upper-bound as sum of relative entropy divergences to a set of singleton models, induced by the set of observations. Our alternative motivation unifies the "observation level" and the "model level" view of the EM. As a result, we formulate an online version of the EM algorithm by adding an analogous inertia term which corresponds to the relative entropy divergence to the old model. Our motivation is more widely applicable than the previous approaches and leads to simple online updates for mixture of exponential distributions, hidden Markov models, and the first known online update for Kalman filters. Additionally, the finite sample form of the inertia term lets us derive online updates when there is no closed-form solution. Finally, we extend the analysis to the distributed setting where we motivate a systematic way of combining multiple hidden variable models. Experimentally, we validate the results on synthetic as well as real-world datasets.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Identifying Drift, Diffusion, and Causal Structure from Temporal Snapshots
Analytic estimation of parameters of stochastic volatility diffusion models with exponential-affine characteristic function for currency option pricing
A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net Models
Robust Spatiotemporal Epidemic Modeling with Integrated Adaptive Outlier Detection
IMC-PINN-FE: A Physics-Informed Neural Network for Patient-Specific Left Ventricular Finite Element Modeling with Image Motion Consistency and Biomechanical Parameter Estimation
Adjustment for Confounding using Pre-Trained Representations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.