paper-with-me

Papers

Integral Probability Metrics PAC-Bayes Bounds

2022-07-01 · Ron Amit, Baruch Epstein, Shay Moran, Ron Meir

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.

📄 PDF Abstract BibTeX arXiv:2207.00614

Code (1)

ron-amit/pac_bayes_reg 공식 구현 pytorch

Tasks

Generalization BoundsStyle Generalization

Similar Papers 제목 키워드 기반

Bayesian Posterior Perturbation Analysis with Integral Probability Metrics

2023-03-02 · Alfredo Garbuno-Inigo, Tapio Helin, Franca Hoffmann, Bamdad Hosseini

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 Inference

Optimal Bounds between f-Divergences and Integral Probability Metrics

2020-01-01 · ICML 2020 1 · Rohit Agrawal, Thibaut Horel

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…

LEMMA

Optimal Bounds between $f$-Divergences and Integral Probability Metrics

2020-06-10 · Rohit Agrawal, Thibaut Horel

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…

LEMMA

Variational Bayesian Methods for Stochastically Constrained System Design Problems

2020-01-06 · pproximateinference AABI Symposium 2019 12 · Prateek Jaiswal, Harsha Honnappa, Vinayak A. Rao

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

2024-09-10 · Vincent Menden, Yahya Saleh, Armin Iske

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