Deep Gamblers: Learning to Abstain with Portfolio Theory Liu Ziyin Liu (UTokyo), Zhikang T. Wang(UTokyo), Paul Liang(CMU), Ruslan salakhutdinov (CMU), Louis-Philippe Morency (CMU), Masahito Ueda (UTokyo), Classification and the Inadequacy of loss Want to find: = arg max ఏ Pr(|) In practice, minimize ( loss): min ఏ − log (|) The proposed method: the gambler’s loss max log = max ୀଵ log( + ) SOTA Performance… Surprising Benefit: -Training with gambler’s loss reduces overfit -Improved performance when noisy label is present The Learned Representation is Better Separable: Toy Example: Image Rotation.. Toy Example: Identifying Disconfident Images.. Intuition: Prediction as Horse Race Horse Race with Reservation horses Betting strategy: ∑ ெ ୀଵ → ∑ ୀ Chance of winning: Payoff if we bet on the winning horse: Return after winning: = → + Objective: maximize doubling rate: max = max log = max ୀଵ log( + ) Classification Problem = Betting problem with Reservation with = 1, =0 Classification Problem ≤ Betting problem with Reservation