Integral Probability Metrics PAC-Bayes Bounds
We present a PAC-Bayes-style generalization bound which enables the replacement of the KL-divergence with a variety of Integral Probability Metrics (IPM). We provide instances of this bound with the IPM being the total variation metric and the Wasserstein distance. A notable feature of the obtained bounds is that they naturally interpolate between classical uniform convergence bounds in the worst case (when the prior and posterior are far away from each other), and improved bounds in favorable cases (when the posterior and prior are close). This illustrates the possibility of reinforcing classical generalization bounds with algorithm- and data-dependent components, thus making them more suitable to analyze algorithms that use a large hypothesis space.
Code (1)
Tasks
Generalization BoundsStyle GeneralizationSimilar Papers 제목 키워드 기반
Bayesian Posterior Perturbation Analysis with Integral Probability Metrics
In recent years, Bayesian inference in large-scale inverse problems found in science, engineering and machine learning has gained significant attention. This paper examines the robustness of the Bayesian approach by anal…
Bayesian InferenceOptimal Bounds between f-Divergences and Integral Probability Metrics
The families of f-divergences (e.g. the Kullback-Leibler divergence) and Integral Probability Metrics (e.g. total variation distance or maximum mean discrepancies) are commonly used in optimization and estimation. In thi…
LEMMAOptimal Bounds between $f$-Divergences and Integral Probability Metrics
The families of $f$-divergences (e.g. the Kullback-Leibler divergence) and Integral Probability Metrics (e.g. total variation distance or maximum mean discrepancies) are widely used to quantify the similarity between pro…
LEMMAVariational Bayesian Methods for Stochastically Constrained System Design Problems
We study system design problems stated as parameterized stochastic programs with a chance-constraint set. We adopt a Bayesian approach that requires the computation of a posterior predictive integral which is usually int…
Bounds on the Generalization Error in Active Learning
We establish empirical risk minimization principles for active learning by deriving a family of upper bounds on the generalization error. Aligning with empirical observations, the bounds suggest that superior query algor…
Active LearningInformativeness