Learning Exponential Families in High-Dimensions:
Strong Convexity and Sparsity
Sham Kakade, Ohad Shamir, Karthik Sridharan and Ambuj Tewari
In: AISTATS 2010(2010).
The versatility of exponential families, along
with their attendant convexity properties,
make them a popular and effective statistical
model. A central issue is learning these
models in high-dimensions when the optimal
parameter vector is sparse. This work characterizes
a certain strong convexity property
of general exponential families, which allows
their generalization ability to be quantified.
In particular, we show how this property can
be used to analyze generic exponential families
under L1 regularization.