Recently, neural heuristics based on deep reinforcement learning have exhibited promise in solving multi-objective combinatorial optimization problems (MO-COPs).

Such direct sim2real transfer is not guaranteed to succeed, however, and in cases where it fails, it is unclear how to best utilize the simulator. In this work, we show that in many regimes, while direct sim2real transfer may fail, we can utilize the simulator to learn a set of exploratory policies which enable efficient exploration in the real world.

Our contributions are summarized as follows.

In many search applications related to passage retrieval, text entailment, and sub-graph search, the query and each'document' is a set of elements, with a document

Pruning methods for neural networks [LeCun et al., 1989] replace dense weight matrices by sparse

Concretely, we prove that polynomial-sized message-passing GNN's can learn the

Data-driven algorithm design is a promising, learning-based approach for beyond worst-case analysis of algorithms with tunable parameters. An important open problem is the design of computationally efficient data-driven algorithms for combinatorial algorithm families with multiple parameters.