Timezone: »

 
Poster
On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models
Adarsh Prasad · Alexandru Niculescu-Mizil · Pradeep Ravikumar

Tue Dec 05 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #37
in Posters Tue »

We revisit the classical analysis of generative vs discriminative models for general exponential families, and high-dimensional settings. Towards this, we develop novel technical machinery, including a notion of separability of general loss functions, which allow us to provide a general framework to obtain l∞ convergence rates for general M-estimators. We use this machinery to analyze l∞ and l2 convergence rates of generative and discriminative models, and provide insights into their nuanced behaviors in high-dimensions. Our results are also applicable to differential parameter estimation, where the quantity of interest is the difference between generative model parameters.

Keywords: Learning Theory · Regression
[ Paper] 

Author Information

Adarsh Prasad (Carnegie Mellon University)
Alexandru Niculescu-Mizil (NEC Laboratories America)
Pradeep Ravikumar (Carnegie Mellon University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors