This thesis explores the integration of machine learning (ML) into algorithm design for solving complex combinatorial optimization problems. We focus on solving problems that arise in bilevel optimization, two-stage robust optimization, and phylogenetics. Although these problem classes seem vastly different, they share the common characteristic of being extremely challenging to solve. Current solution methods for these problems are computationally heavy and their solving duration is often impractical for already small-sized instances. Adding a component of machine learning also adds complexity. We primarily attempt to mitigate this effect by proposing learning methods that utilize efficient training data generation schemes that rely on solving sub-problems or are even based on a simple procedure, instead of learning from optimal solutions of many instances similar to the target problem.

Two-stage robust optimization problems constitute one of the hardest optimization problem classes. One of the solution approaches to this class of problems is K-adaptability. This approach simultaneously seeks the best partitioning of the uncertainty set of scenarios into K subsets and optimizes decisions corresponding to each of these subsets. In a general case, it is solved using the K-adaptability branch-and-bound algorithm, which requires exploration of exponentially growing solution trees. To accelerate finding high-quality solutions in such trees, we propose a machine learning-based node selection strategy. In particular, we construct a feature engineering scheme based on general two-stage robust optimization insights, which allows us to train our machine learning tool on a database of resolved branch-and-bound trees and to apply it as is to problems of different sizes and/or types. We experimentally show that using our learned node selection strategy outperforms a vanilla, random node selection strategy when tested on problems of the same type as the training problems as well as in cases when the K-value or the problem size differs from the training ones.

Robust optimization provides a mathematical framework for modeling and solving decision-making problems under worst-case uncertainty. This work addresses two-stage robust optimization (2RO) problems (also called adjustable robust optimization), wherein first-stage and second-stage decisions are made before and after uncertainty is realized, respectively. This results in a nested min-max-min optimization problem which is extremely challenging computationally, especially when the decisions are discrete. We propose Neur2RO, an efficient machine learning-driven instantiation of column-and-constraint generation (CCG), a classical iterative algorithm for 2RO. Specifically, we learn to estimate the value function of the second-stage problem via a novel neural network architecture that is easy to optimize over by design. Embedding our neural network into CCG yields high-quality solutions quickly as evidenced by experiments on two 2RO benchmarks, knapsack and capital budgeting. For knapsack, Neur2RO finds solutions that are within roughly % of the best-known values in a few seconds compared to the three hours of the state-of-the-art exact branch-and-price algorithm; for larger and more complex instances, Neur2RO finds even better solutions. For capital budgeting, Neur2RO outperforms three variants of the -adaptability algorithm, particularly on the largest instances, with a to -fold reduction in solution time. Our code and data are available at https://github.com/khalil-research/Neur2RO.

The Hybridization problem asks to reconcile a set of conflicting phylogenetic trees into a single phylogenetic network with the smallest possible number of reticulation nodes. This problem is computationally hard and previous solutions are limited to small and/or severely restricted data sets, for example, a set of binary trees with the same taxon set or only two non-binary trees with non-equal taxon sets. Building on our previous work on binary trees, we present FHyNCH, the first algorithmic framework to heuristically solve the Hybridization problem for large sets of multifurcating trees whose sets of taxa may differ. Our heuristics combine the cherry-picking technique, recently proposed to solve the same problem for binary trees, with two carefully designed machine-learning models. We demonstrate that our methods are practical and produce qualitatively good solutions through experiments on both synthetic and real data sets.

Phylogenetic networks are used to represent the evolutionary history of species. Recently, the new class of orchard networks was introduced, which were later shown to be interpretable as trees with additional horizontal arcs. This makes the network class ideal for capturing evolutionary histories that involve horizontal gene transfers. Here, we study the minimum number of additional leaves needed to make a network orchard. We demonstrate that computing this proximity measure for a given network is NP-hard and describe a tight upper bound. We also give an equivalent measure based on vertex labellings to construct a mixed integer linear programming formulation. Our experimental results, which include both real-world and synthetic data, illustrate the efficiency of our implementation.

Background: Combining a set of phylogenetic trees into a single phylogenetic network that explains all of them is a fundamental challenge in evolutionary studies. Existing methods are computationally expensive and can either handle only small numbers of phylogenetic trees or are limited to severely restricted classes of networks. Results: In this paper, we apply the recently-introduced theoretical framework of cherry picking to design a class of efficient heuristics that are guaranteed to produce a network containing each of the input trees, for practical-size datasets consisting of binary trees. Some of the heuristics in this framework are based on the design and training of a machine learning model that captures essential information on the structure of the input trees and guides the algorithms towards better solutions. We also propose simple and fast randomised heuristics that prove to be very effective when run multiple times. Conclusions: Unlike the existing exact methods, our heuristics are applicable to datasets of practical size, and the experimental study we conducted on both simulated and real data shows that these solutions are qualitatively good, always within some small constant factor from the optimum. Moreover, our machine-learned heuristics are one of the first applications of machine learning to phylogenetics and show its promise.

Combining a set of phylogenetic trees into a single phylogenetic network that explains all of them is a fundamental challenge in evolutionary studies. In this paper, we apply the recently-introduced theoretical framework of cherry picking to design a class of heuristics that are guaranteed to produce a network containing each of the input trees, for practical-size datasets. The main contribution of this paper is the design and training of a machine learning model that captures essential information on the structure of the input trees and guides the algorithms towards better solutions. This is one of the first applications of machine learning to phylogenetic studies, and we show its promise with a proof-of-concept experimental study conducted on both simulated and real data consisting of binary trees with no missing taxa.