no code implementations • ICML 2020 • Henry Reeve, Ata Kaban
We investigate the challenge of multi-output learning, where the goal is to learn a vector-valued function based on a supervised data set.
no code implementations • 2 Jun 2021 • Henry W. J. Reeve, Ata Kaban
For each of these tasks, our strategy is to develop a tight upper bound on the compressibility function, and by doing so we discover distributional conditions of geometric nature under which the compressive algorithm attains minimax-optimal rates up to at most poly-logarithmic factors.
no code implementations • 22 Feb 2020 • Henry WJ Reeve, Ata Kaban
We investigate the challenge of multi-output learning, where the goal is to learn a vector-valued function based on a supervised data set.
no code implementations • 11 Jun 2019 • Henry W. J. Reeve, Ata Kaban
We consider classification in the presence of class-dependent asymmetric label noise with unknown noise probabilities.
no code implementations • 14 Feb 2019 • Henry W. J. Reeve, Ata Kaban
In order to obtain finite sample rates, previous approaches to classification with unknown class-conditional label noise have required that the regression function is close to its extrema on sets of large measure.
no code implementations • 26 Sep 2013 • Jakramate Bootkrajang, Ata Kaban
Boosting is known to be sensitive to label noise.