Intensity,as defined in the classical temporal point process(TPP) sense, can be interpreted as the expected number of eventsz z0 withinthetimeinterval[t,t+dt].

A major drawback of continuous methods isthat the optimal hierarchyofsoft scores might not align with their discrete counterparts.

In Section 4, we argue that there exists a discrepancy between over-smoothing based theoretical results and the practical capabilities of deep GCN models, demonstrating that over-smoothing is not the key factor that leads to the performance degradation in deeper GCNs.

Wealsoprovidelowerbounds proving the worst-case optimality of our algorithms for CVaR and a penalized versionoftheχ2 problem.

We provide online convex optimization algorithms that guarantee improved fullmatrix regret bounds. These algorithms extend prior work in several ways. First, we seamlessly allow for the incorporation of constraints without requiring unknown oracle-tuning for any learning rate parameters. Second, we improve the regret analysis of the full-matrix AdaGrad algorithm by suggesting a better learning rate value and showing how to tune the learning rate to this value on-the-fly. Third, all our bounds are obtained via a general framework for constructing regret bounds that depend on an arbitrary sequence of norms.