Search Results for author:
Found 22 papers, 1 papers with code
A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix
Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data during its entire lifetime.
Concentration of tempered posteriors and of their variational approximations
While Bayesian methods are extremely popular in statistics and machine learning, their application to massive datasets is often challenging, when possible at all.
Regret Bounds for Lifelong Learning
We consider the problem of transfer learning in an online setting.
Simpler PAC-Bayesian Bounds for Hostile Data
In these bounds the Kullack-Leibler divergence is replaced with a general version of Csisz\'ar's $f$-divergence.
An Oracle Inequality for Quasi-Bayesian Non-Negative Matrix Factorization
The aim of this paper is to provide some theoretical understanding of quasi-Bayesian aggregation methods non-negative matrix factorization.
1-bit Matrix Completion: PAC-Bayesian Analysis of a Variational Approximation
We also study the performance of this variational approximation through PAC-Bayesian learning bounds.
On the properties of variational approximations of Gibbs posteriors
We consider instead variational approximations of the Gibbs posterior, which are fast to compute.
Bayesian matrix completion: prior specification
While the behaviour of algorithms based on nuclear norm minimization is now well understood, an as yet unexplored avenue of research is the behaviour of Bayesian algorithms in this context.
PAC-Bayesian AUC classification and scoring
We also extend our method to a class of non-linear score functions, essentially leading to a nonparametric procedure, by considering a Gaussian process prior.
Bayesian methods for low-rank matrix estimation: short survey and theoretical study
The problem of low-rank matrix estimation recently received a lot of attention due to challenging applications.
Exponential inequalities for nonstationary Markov Chains
In this paper, we extend the basic tools of Dedecker and Fan (2015) to nonstationary Markov chains.
A Generalization Bound for Online Variational Inference
Our work in this paper presents theoretical justifications in favor of online algorithms relying on approximate Bayesian methods.
High dimensional VAR with low rank transition
We propose a vector auto-regressive (VAR) model with a low-rank constraint on the transition matrix.
MMD-Bayes: Robust Bayesian Estimation via Maximum Mean Discrepancy
In some misspecified settings, the posterior distribution in Bayesian statistics may lead to inconsistent estimates.
Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence
Many works in statistics aim at designing a universal estimation procedure, that is, an estimator that would converge to the best approximation of the (unknown) data generating distribution in a model, without any assumption on this distribution.
Non-exponentially weighted aggregation: regret bounds for unbounded loss functions
We tackle the problem of online optimization with a general, possibly unbounded, loss function.
Meta-strategy for Learning Tuning Parameters with Guarantees
We consider an online meta-learning scenario, and we propose a meta-strategy to learn these parameters from past tasks.
Deviation inequalities for stochastic approximation by averaging
We introduce a class of Markov chains, that contains the model of stochastic approximation by averaging and non-averaging.
User-friendly introduction to PAC-Bayes bounds
Aggregated predictors are obtained by making a set of basic predictors vote according to some weights, that is, to some probability distribution.
Variance-Aware Estimation of Kernel Mean Embedding
An important feature of kernel mean embeddings (KME) is that the rate of convergence of the empirical KME to the true distribution KME can be bounded independently of the dimension of the space, properties of the distribution and smoothness features of the kernel.
PAC-Bayesian Offline Contextual Bandits With Guarantees
This paper introduces a new principled approach for off-policy learning in contextual bandits.
Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes
Bernstein's condition is a key assumption that guarantees fast rates in machine learning.
