
Transfer Bayesian Metalearning via Weighted Free Energy Minimization
Metalearning optimizes the hyperparameters of a training procedure, suc...
read it

A unified PACBayesian framework for machine unlearning via information risk minimization
Machine unlearning refers to mechanisms that can remove the influence of...
read it

InformationTheoretic Analysis of Epistemic Uncertainty in Bayesian Metalearning
The overall predictive uncertainty of a trained predictor can be decompo...
read it

An InformationTheoretic Analysis of the Impact of Task Similarity on MetaLearning
Metalearning aims at optimizing the hyperparameters of a model class or...
read it

Free Energy Minimization: A Unified Framework for Modelling, Inference, Learning,and Optimization
The goal of these lecture notes is to review the problem of free energy ...
read it

Transfer MetaLearning: InformationTheoretic Bounds and Information MetaRisk Minimization
Metalearning automatically infers an inductive bias by observing data f...
read it

Conditional Mutual Information Bound for Meta Generalization Gap
Metalearning infers an inductive bias—typically in the form of the hype...
read it

InformationTheoretic Bounds on Transfer Generalization Gap Based on JensenShannon Divergence
In transfer learning, training and testing data sets are drawn from diff...
read it

InformationTheoretic Generalization Bounds for MetaLearning and Applications
Metalearning, or "learning to learn", refers to techniques that infer a...
read it

AddressEvent VariableLength Compression for TimeEncoded Data
Timeencoded signals, such as social network update logs and spiking tra...
read it

Shannon meets von Neumann: A Minimax Theorem for Channel Coding in the Presence of a Jammer
We study the setting of channel coding over a family of channels whose s...
read it

Improved Finite Blocklength Converses for SlepianWolf Coding via Linear Programming
A new finite blocklength converse for the Slepian Wolf coding problem i...
read it
Sharu Theresa Jose
is this you? claim profile