Fair representation learning with a continuous sensitive attribute $S$ requires a representation $Z$ that is statistically independent of $S$. Existing criteria, including generalized demographic parity, the expectation of integral probability metrics (EIPM), and mutual information, enforce this independence by averagi...
Rank confidence sequences are constructed: for every model, a set of ranks that contains its true rank, simultaneously for all models and at all times, at a chosen error level $\alpha$ in finite samples, in finite samples.
TEAM-Design is proposed, a rule that gives every task two replay probabilities, one per baseline, and it is proved that the rule solves this budgeted design problem, and that drawing the replays at random from recorded probabilities still controls the chance of wrongly declaring that the workflow beats both.
CAS (causal active sequential experimentation), which targets evaluation to model-workload pairs and repeats the test as evidence accumulates, to ask whether one assignment stays optimal across every quality table consistent with the evidence.
Noise premium makes the prediction error of adversarial training converge strictly more slowly than the nonparametric minimax benchmark even after balancing approximation and estimation errors, so the proposed noise-debiased adversarial training is proposed.
Yiling Xie, Xiaoming Huo· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
