Technical Program

Paper Detail

Paper IDL.9.3
Paper Title On the alpha-loss Landscape in the Logistic Model
Authors Tyler Sypherd, Arizona State University, United States; Mario Diaz, Universidad Nacional Autónoma de México, Mexico; Lalitha Sankar, Gautam Dasarathy, Arizona State University, United States
Session L.9: Learning Methods and Networks
Presentation Lecture
Track Statistics and Learning Theory
Manuscript  Click here to download the manuscript
Virtual Presentation  Click here to watch in the Virtual Symposium
Abstract We analyze the optimization landscape of a recently introduced tunable class of loss functions called alpha-loss, alpha in (0,infinity], in the logistic model. This family encapsulates the exponential loss (alpha = 1/2), the log-loss (alpha = 1), and the 0-1 loss (alpha = infinity) and contains compelling properties that enable the practitioner to discern among a host of operating conditions relevant to emerging learning methods. Specifically, we study the evolution of the optimization landscape of alpha-loss with respect to alpha using tools drawn from the study of strictly-locally-quasi-convex functions in addition to geometric techniques. We interpret these results in terms of optimization complexity via normalized gradient descent.

Plan Ahead


2021 IEEE International Symposium on Information Theory

11-16 July 2021 | Melbourne, Victoria, Australia

Visit Website!