Approximate Probabilistic Inference for Time-Series Data A Robust Latent Gaussian Model With Temporal Awareness
This addresses the need for robust generative models for varied time series data, which is incremental as it builds on Deep Latent Gaussian Models.
The paper tackles the problem of modeling non-stationary time series data by introducing tDLGM, a probabilistic generative model that captures temporal information and is robust to data errors, showing it can reconstruct and generate complex data while being robust against noise and faulty data.
The development of robust generative models for highly varied non-stationary time series data is a complex yet important problem. Traditional models for time series data prediction, such as Long Short-Term Memory (LSTM), are inefficient and generalize poorly as they cannot capture complex temporal relationships. In this paper, we present a probabilistic generative model that can be trained to capture temporal information, and that is robust to data errors. We call it Time Deep Latent Gaussian Model (tDLGM). Its novel architecture is inspired by Deep Latent Gaussian Model (DLGM). Our model is trained to minimize a loss function based on the negative log loss. One contributing factor to Time Deep Latent Gaussian Model (tDLGM) robustness is our regularizer, which accounts for data trends. Experiments conducted show that tDLGM is able to reconstruct and generate complex time series data, and that it is robust against to noise and faulty data.