Learning Combinatorial Structures via Markov Random Fields with Sampling through Lovász Local Lemma

by   Nan Jiang, et al.

Generative models for learning combinatorial structures have transformative impacts in many applications. However, existing approaches fail to offer efficient and accurate learning results. Because of the highly intractable nature of the gradient estimation of the learning objective subject to combinatorial constraints. Existing gradient estimation methods would easily run into exponential time/memory space, or incur huge estimation errors due to improper approximation. We develop NEural Lovasz Sampler (Nelson), a neural network based on Lovász Local Lemma (LLL). We show it guarantees to generate samples satisfying combinatorial constraints from the distribution of the constrained Markov Random Fields model (MRF) under certain conditions. We further present a fully differentiable contrastive-divergence-based learning framework on constrained MRF (Nelson-CD). Meanwhile, Nelson-CD being fully differentiable allows us to take advantage of the parallel computing power of GPUs, resulting in great efficiency. Experimental results on three real-world combinatorial problems reveal that Nelson learns to generate 100 structures. In comparison, baselines either time out on large-size data sets or fail to generate valid structures, whereas Nelson scales much better with problem size. In addition, Nelson outperforms baselines in various learning metrics, such as log-likelihood and MAP scores.


page 1

page 2

page 3

page 4


Efficient Parallel Estimation for Markov Random Fields

We present a new, deterministic, distributed MAP estimation algorithm fo...

Linear and Parallel Learning of Markov Random Fields

We introduce a new embarrassingly parallel parameter learning algorithm ...

Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealing

Markov random fields (MRFs) are difficult to evaluate as generative mode...

Adversarial Variational Inference and Learning in Markov Random Fields

Markov random fields (MRFs) find applications in a variety of machine le...

Tree-based iterated local search for Markov random fields with applications in image analysis

The maximum a posteriori (MAP) assignment for general structure Markov r...

Products of Hidden Markov Models: It Takes N>1 to Tango

Products of Hidden Markov Models(PoHMMs) are an interesting class of gen...

Differentiable Equilibrium Computation with Decision Diagrams for Stackelberg Models of Combinatorial Congestion Games

We address Stackelberg models of combinatorial congestion games (CCGs); ...

Please sign up or login with your details

Forgot password? Click here to reset