Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness

Nov 28, 2022



Recent work has established that the conditional mutual information (CMI) framework of Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees in terms of algorithmic stability, VC dimension, and related complexity measures for conventional learning (Harutyunyan et al., 2021, Haghifam et al., 2021). Hence, it provides a unified method for establishing generalization bounds. In meta learning, there has so far been a divide between information-theoretic results and results from classical learning theory. In this work, we take a first step toward bridging this divide. Specifically, we present novel generalization bounds for meta learning in terms of the evaluated CMI (e-CMI). To demonstrate the expressiveness of the e-CMI framework, we apply our bounds to a representation learning setting, with n samples from n̂ tasks parameterized by functions of the form f_i ∘ h. Here, each f_i(·) is a task-specific function, and h(·) is the shared representation. For this setup, we show that the e-CMI framework yields a bound that scales as √(𝒞(ℋ)/(nn̂) + 𝒞(ℱ)/n), where 𝒞(·) denotes a complexity measure of the hypothesis class. This scaling behavior coincides with the one reported in Tripuraneni et al. (2020) using Gaussian complexity.


Store presentation

Should this presentation be stored for 1000 years?

How do we store presentations

Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%


Recommended Videos

Presentations on similar topic, category or speaker

Interested in talks like this? Follow NeurIPS 2022