Niepert, M; Minervini, P; Franceschi, L; (2021) Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions. In: Ranzato, M and Beygelzimer, A and Dauphin, Y and Liang, PS and Wortman Vaughan, J, (eds.) Advances in Neural Information Processing Systems 34 (NeurIPS 2021). (pp. pp. 14567-14579). NeurIPS

Preview

Text implicit_mle_backpropagating_t.pdf - Published Version Download (659kB) | Preview

Abstract

Combining discrete probability distributions and combinatorial optimization problems with neural network components has numerous applications but poses several challenges. We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete exponential family distributions and differentiable neural components. I-MLE is widely applicable as it only requires the ability to compute the most probable states and does not rely on smooth relaxations. The framework encompasses several approaches such as perturbation-based implicit differentiation and recent methods to differentiate through black-box combinatorial solvers. We introduce a novel class of noise distributions for approximating marginals via perturb-and-MAP. Moreover, we show that I-MLE simplifies to maximum likelihood estimation when used in some recently studied learning settings that involve combinatorial solvers. Experiments on several datasets suggest that I-MLE is competitive with and often outperforms existing approaches which rely on problem-specific relaxations.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item