Fetching the paper…
Reading the bibliography…
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).
A generalization of Sauer’s lemma
D. Haussler and P. M. Long · 1995
Earlier work this paper cites.
Multitask learning
R. Caruana · 1997
Earlier work this paper cites.
Learning to Learn: Introduction and Overview
S. Thrun and L. Pratt · 1998
Earlier work this paper cites.
Some PAC-Bayesian theorems
D. A. McAllester · 1998
Earlier work this paper cites.
A model of inductive bias learning
J. Baxter · 2000
Earlier work this paper cites.
Large Margin Multi-category Discriminant Models and Scale-sensitive Psi-dimensions
Y. Guermeur · 2006
Earlier work this paper cites.
Linear algorithms for online multitask classification
G. Cavallanti, N. Cesa-Bianchi, and C. Gentile · 2010
Earlier work this paper cites.
Oracle inequalities and optimal inference under group sparsity
K. Lounici, M. Pontil, S. van de Geer, and A. B. Tsybakov · 2011
Earlier work this paper cites.
Excess risk bounds for multitask learning with trace norm regularization
M. Pontil and A. Maurer · 2013
Earlier work this paper cites.
A PAC-Bayesian tutorial with a dropout bound
D.A. McAllester · 2013
Earlier work this paper cites.
A PAC-Bayesian bound for lifelong learning
A. Pentina and C. Lampert · 2014
Earlier work this paper cites.
The benefit of multitask representation learning
A. Maurer, M. Pontil, and B. Romera-Paredes · 2016
Earlier work this paper cites.
Controlling bias in adaptive data analysis using information theory
D. Russo and J. Zou · 2016
Earlier work this paper cites.
Information-theoretic analysis of generalization capability of learning algorithms
A. Xu and M. Raginsky · 2017
Cited alongside, same era.
Bilevel programming for hyperparameter optimization and meta-learning
L. Franceschi, P. Frasconi, S. Salzo, R. Grazzi, and M. Pontil · 2018
Cited alongside, same era.
Meta-learning by adjusting priors based on extended PAC-Bayes theory
R. Amit and R. Meir · 2018
Cited alongside, same era.
Bayesian model-agnostic meta-learning
J. Yoon, T. Kim, O. Dia, S. Kim, Y. Bengio, and S. Ahn · 2018
Cited alongside, same era.
Provable guarantees for gradient-based meta-learning
M.F. Balcan, M. Khodak, and A. Talwalkar · 2019
Cited alongside, same era.
Information-theoretic generalization bounds for SGLD via data-dependent estimates
J. Negrea, M. Haghifam, G. K. Dziugaite, A. Khisti, and D.M. Roy · 2019
Generalization bounds via information density and conditional information density
F. Hellström and G. Durisi · 2020
Later among the works it cites.
Data-dependent PAC-Bayesian bounds in the random-subset setting with applications to neural networks
F. Hellström and G. Durisi · 2021
Later among the works it cites.
Information-theoretic generalization bounds for black-box learning algorithms
H. Harutyunyan, M. Raginsky, G. Ver Steeg, and A. Galstyan · 2021
Later among the works it cites.
User-friendly introduction to PAC-Bayes bounds
P. Alquier · 2021
Later among the works it cites.
Information-theoretic generalization bounds for meta-learning and applications
S. T. Jose and O. Simeone · 2021
Later among the works it cites.
Generalization bounds for meta-learning: An information-theoretic analysis
Q. Chen, C. Shui, and M. Marchand · 2021
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
High-Dimensional Statistics: a Non-Asymptotic Viewpoint
M. J. Wainwright · 2019
Cited alongside, same era.
On the theory of transfer learning: The importance of task diversity
N. Tripuraneni, M. Jordan, and C. Jin · 2020
Cited alongside, same era.
Tightening mutual information-based bounds on generalization error
Y. Bu, S. Zou, and V. V. Veeravalli · 2020
Cited alongside, same era.
Reasoning about generalization via conditional mutual information
T. Steinke and L. Zakynthinou · 2020
Cited alongside, same era.
Sharpened generalization bounds based on conditional mutual information and an application to noisy, iterative algorithms
M. Haghifam, J. Negrea, A. Khisti, D. M. Roy, and G. K. Dziugaite · 2020
Cited alongside, same era.
On random subset generalization error bounds and the stochastic gradient langevin dynamics algorithm
B. Rodríguez-Gálvez, G. Bassi, R. Thobaben, and M. Skoglund · 2020
Cited alongside, same era.
Later among the works it cites.
PACOH: Bayes-optimal meta-learning with PAC-guarantees
J. Rothfuss, V. Fortuin, M. Josifoski, and A. Krause · 2021
Later among the works it cites.
Improved generalization risk bounds for meta-learning with PAC-Bayes-kl analysis
J. Guan, Z. Lu, and Y. Liu · 2021
Later among the works it cites.
Generalization bounds for meta-learning via PAC-Bayes and uniform stability
A. Farid and A. Majumdar · 2021
Later among the works it cites.
Conditional mutual information-based generalization bound for meta learning
A. Rezazadeh, S. T. Jose, G. Durisi, and O. Simeone · 2021
Later among the works it cites.
Transfer meta-learning: Information- theoretic bounds and information meta-risk minimization
S. T. Jose, O. Simeone, and G. Durisi · 2022
Closest in time.
PAC-Bayesian lifelong learning for multi-armed bandits
H. Flynn, D. Reeb, M. Kandemir, and J. Peters · 2022
Closest in time.