Best of both worlds: integrating principled matched-filtering searches with AI/ML tools

In the infinite data and compute limit, machine learning (ML) methods can be optimal, however this idealistic situation is scarcely realized in practice. On the other hand, principled data-analysis methods are robust, but they make simplistic assumptions (e.g., the noise is roughly Gaussian). I will present how ML algorithms can enhance matched-filtering pipelines by: (i) generating optimal template banks (ii) weighting templates to downplay unphysical binary configurations (iii) mitigating non-Gaussian noise. Incorporating these advancements in the IAS search pipeline, I will present new detections of black holes in the astrophysically significant pair-instability mass gap and IMBH mass ranges.