Minimum Probability Flow Learning

Abstract

Fitting probabilistic models to data is often difficult, due to the general intractability of the partition function and its derivatives. Here we propose a new parameter estimation technique that does not require computing an intractable normalization factor or sampling from the equilibrium distribution of the model. This is achieved by establishing dynamics that would transform the observed data distribution into the model distribution, and then setting as the objective the minimization of the KL divergence between the data distribution and the distribution produced by running the dynamics for an infinitesimal time. Score matching, minimum velocity learning, and certain forms of contrastive divergence are shown to be special cases of this learning technique. We demonstrate parameter estimation in Ising models, deep belief networks and an independent component analysis model of natural scenes. In the Ising model case, current state of the art techniques are outperformed by at least an order of magnitude in learning time, with lower error in recovered coupling parameters.

Updated to match ICML conference proceedings

References in corpus (2)

• Weak pairwise correlations imply strongly correlated network states in a neural population
• Interpretation and Generalization of Score Matching

Cited by in corpus (14)

• Generative Modeling by Estimating Gradients of the Data Distribution
• A note on the evaluation of generative models
• Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods
• In All Likelihood, Deep Belief Is Not Enough
• Neural Autoregressive Distribution Estimation
• Minimum Stein Discrepancy Estimators
• Exponential Family Estimation via Adversarial Dynamics Embedding
• Partition Functions from Rao-Blackwellized Tempered Sampling
• Bi-level Score Matching for Learning Energy-based Latent Variable Models
• Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
• A Unified Dynamic Approach to Sparse Model Selection
• The Ising decoder: reading out the activity of large neural ensembles
• Convenient Interface to Inverse Ising (ConIII): A Python 3 Package for Solving Ising-Type Maximum Entropy Models
• Biologically Plausible Sequence Learning with Spiking Neural Networks