Timezone: »

 
Likelihood Score under Generalized Self-Concordance
Lang Liu · Zaid Harchaoui
Event URL: https://openreview.net/forum?id=AxRUi1XESo »

We show how, under a generalized self-concordance assumption and possible model misspecification, we can establish non-asymptotic bounds on the normalized likelihood score when using maximum likelihood or score matching. The tail behavior is governed by an effective dimension corresponding to the trace of the sandwich covariance. We also show how our non-asymptotic approach allows us to obtain confidence set for the estimator and analyze Rao's score test.

Author Information

Lang Liu (University of Washington)
Zaid Harchaoui (University of Washington)

More from the Same Authors