A key step in any resonant anomaly detection search is accurate modeling of the background distribution in each signal region. Data-driven methods like CATHODE accomplish this by training separate generative models on the complement of each signal region, and interpolating them into their corresponding signal regions. Having to re-train the generative model on essentially the entire dataset for each signal region is a major computational cost in a typical sliding window search with many signal regions. Here, we present SIGMA, a new, fully data-driven, computationally-efficient method for estimating background distributions. The idea is to train a single generative model on all of the data and interpolate its parameters in sideband regions in order to obtain a model for the background in the signal region. The SIGMA method significantly reduces the computational cost compared to previous approaches, while retaining a similar high quality of background modeling and sensitivity to anomalous signals.

Trumpeting a message that he conceded might be different from peers, Stefan Golling, a member of Munich Re Board of Management, said that Munich Re remains bullish on the cyber insurance and reinsurance markets. In fact, "if insurers and reinsurers shy away from the cyber market, they will not survive," said Golling, Munich Re board member for Global Clients/North America, during a presentation the European reinsurer's virtual Rendez-Vous presentation. He noted media reports of a hardening cyber insurance market, reduced available capacity and narrower carrier and reinsurer appetites for cyber risk. Those shouldn't scare insurers and reinsurers away, Golling said. "If we want to remain relevant in this industry, relevant for our clients, then we need to find solutions for cyber. And we will," he said.