We present a machine learning approach for model-independent new physics searches. The corresponding algorithm is powered by recent large-scale implementations of kernel methods, nonparametric learning algorithms that can approximate any continuous …
Searching for new physics, i.e., physical laws that go beyond the reference models, is the absolute priority of the field. In this thesis, a novel machine learning approach for model-independent new physics searches is presented, based on the work by …
We present a novel kernel-based anomaly detection algorithm for modelindependent new physics searches. The model is based on a re-weighted version of kernel logistic regression and it aims at learning the likelihood ratio test statistics from …
The Level 1 (L1) trigger at CMS uses coarse-grained information to search for signatures of interesting physics. L1 scouting is a new paradigm for data collection at CMS which could help in the early identification of promising potential signals, …