Self-Adapting Noise-Contrastive Estimation for Energy-Based Models
This addresses a practical bottleneck in training energy-based models for researchers in generative modeling, though it appears incremental as it builds on existing noise-contrastive estimation methods.
The paper tackles the challenge of training energy-based models with noise-contrastive estimation by proposing a self-adapting algorithm that uses static instances of the model as the noise distribution, eliminating the need for an auxiliary noise model and showing that shorter update intervals improve synthesis quality.
Training energy-based models (EBMs) with noise-contrastive estimation (NCE) is theoretically feasible but practically challenging. Effective learning requires the noise distribution to be approximately similar to the target distribution, especially in high-dimensional domains. Previous works have explored modelling the noise distribution as a separate generative model, and then concurrently training this noise model with the EBM. While this method allows for more effective noise-contrastive estimation, it comes at the cost of extra memory and training complexity. Instead, this thesis proposes a self-adapting NCE algorithm which uses static instances of the EBM along its training trajectory as the noise distribution. During training, these static instances progressively converge to the target distribution, thereby circumventing the need to simultaneously train an auxiliary noise model. Moreover, we express this self-adapting NCE algorithm in the framework of Bregman divergences and show that it is a generalization of maximum likelihood learning for EBMs. The performance of our algorithm is evaluated across a range of noise update intervals, and experimental results show that shorter update intervals are conducive to higher synthesis quality.