Timezone: »

 
Poster
On Empirical Risk Minimization with Dependent and Heavy-Tailed Data
Abhishek Roy · Krishnakumar Balasubramanian · Murat Erdogdu

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @
in Poster Session 4 »
In this work, we establish risk bounds for Empirical Risk Minimization (ERM) with both dependent and heavy-tailed data-generating processes. We do so by extending the seminal works~\cite{pmlr-v35-mendelson14, mendelson2018learning} on the analysis of ERM with heavy-tailed but independent and identically distributed observations, to the strictly stationary exponentially $\beta$-mixing case. We allow for the interaction between the noise and inputs to be even polynomially heavy-tailed, which covers a significantly large class of heavy-tailed models beyond what is analyzed in the learning theory literature. We illustrate our theoretical results by obtaining rates of convergence for high-dimensional linear regression with dependent and heavy-tailed data.
Keywords: Theory

Author Information

Abhishek Roy (University of California, Davis)
Krishnakumar Balasubramanian (University of California, Davis)
Murat Erdogdu (University of Toronto)

More from the Same Authors