3 papers
stat.ML2026
Overfitting and Generalizing with (PAC) Bayesian Prediction in Noisy Binary Classification
Xiaohan Zhu, Mesrob I. Ohannessian, Nathan Srebro
We consider a PAC-Bayes type learning rule for binary classification, balancing the training error of a randomized ''posterior'' predictor with its KL divergence to a pre-specified…
stat.ML2025
Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification
Xiaohan Zhu, Nathan Srebro
We provide a complete characterization of the entire regularization curve of a modified two-part-code Minimum Description Length (MDL) learning rule for binary classification, base…
math.PR2025
Tight Bounds on the Binomial CDF, and the Minimum of i.i.d Binomials, in terms of KL-Divergence
Xiaohan Zhu, Mesrob I. Ohannessian, Nathan Srebro
We provide finite sample upper and lower bounds on the Binomial tail probability which are a direct application of Sanov's theorem. We then use these to obtain high probability upp…