We introduce ACMN, a new method for learning efficient Markov networks with arbitrary conjunctive features, as long as they admit efficient inference.Expand

The Libra Toolkit is a collection of algorithms for learning and inference with discrete probabilistic models, including Bayesian networks, Markov networks, dependency networks, and sum-product networks.Expand

We present the first discriminative structure learning algorithm for ACs, DACLearn (Discriminative AC Learner), which optimizes conditional log-likelihood.Expand

The discrepancy between maximum likelihood estimation (MLE) and task measures such as BLEU score has been studied before for autoregressive neural machine translation (NMT).Expand

We use efficient truncated randomized search in this reward function to train structured prediction energy networks, which provide efficient test-time inference using gradient-based search on a smooth, learned representation of the score landscape, and have previously yielded state-of-the-art results in structured prediction.Expand

This paper introduces rank-based training of structured prediction energy networks using gradient descent and minimizes the ranking violation of the sampled structures with respect to a scalar scoring function defined with domain knowledge.Expand

We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation function from a family of solutions to an ordinary differential equation.Expand