Papers › A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalization

A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalization

5 Jun 2019arXiv:1906.02314archive 2025-07-28

Tyler Sypherd, Mario Diaz, John Kevin Cava, Gautam Dasarathy, Peter Kairouz, Lalitha Sankar

We introduce a tunable loss function called α-loss, parameterized by α∈(0,∞], which interpolates between the exponential loss (α= 1/2), the log-loss (α= 1), and the 0-1 loss (α= ∞), for the machine learning setting of classification. Theoretically, we illustrate a fundamental connection between α-loss and Arimoto conditional entropy, verify the classification-calibration of α-loss in order to demonstrate asymptotic optimality via Rademacher complexity generalization techniques, and build-upon a notion called strictly local quasi-convexity in order to quantitatively characterize the optimization landscape of α-loss. Practically, we perform class imbalance, robustness, and classification experiments on benchmark image datasets using convolutional-neural-networks. Our main practical conclusion is that certain tasks may benefit from tuning α-loss away from log-loss (α= 1), and to this end we provide simple heuristics for the practitioner. In particular, navigating the α hyperparameter can readily provide superior model robustness to label flips (α> 1) and sensitivity to imbalanced classes (α< 1).

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sankarlab/alphaloss officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationGeneral ClassificationRobust classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections