Recorded 27 February 2024. Pasin Manurangasi of Google Thailand presents "The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise" at IPAM's EnCORE Workshop on Computational vs Statistical Gaps in Learning and Optimization. Abstract: We study the computational complexity of adversarially robust proper learning of halfspaces in the distribution-independent agnostic PAC model, with a focus on L_p perturbations. We give a computationally efficient learning algorithm and a nearly matching computational hardness result for this problem. An interesting implication of our findings is that the L_8 perturbations case is provably computationally harder than the case 2 = p 8. Joint work with Ilias Diakonikolas and Daniel M. Kane. Learn more online at: https://www.ipam.ucla.edu/programs/workshops/encore-workshop-on-computational-vs-statistical-gaps-in-learning-and-optimization/?tab=overview