Search Results for author:
Found 12 papers, 2 papers with code
Upper Bounds on the Generalization Error of Private Algorithms for Discrete Data
In this work, we study the generalization capability of algorithms from an information-theoretic perspective.
A Variational Approach to Privacy and Fairness
In this article, we propose a new variational approach to learn private and/or fair representations.
On Random Subset Generalization Error Bounds and the Stochastic Gradient Langevin Dynamics Algorithm
In this work, we unify several expected generalization error bounds based on random subsets using the framework developed by Hellstr\"om and Durisi [1].
Tighter expected generalization error bounds via Wasserstein distance
This work presents several expected generalization error bounds based on the Wasserstein distance.
Enforcing fairness in private federated learning via the modified method of differential multipliers
This paper introduces an algorithm to enforce group fairness in private federated learning, where users' data does not leave their devices.
An Information-Theoretic Analysis of Bayesian Reinforcement Learning
Building on the framework introduced by Xu and Raginksy [1] for supervised learning problems, we study the best achievable performance for model-based Bayesian reinforcement learning problems.
Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization
To date, no "information-theoretic" frameworks for reasoning about generalization error have been shown to establish minimax rates for gradient descent in the setting of stochastic convex optimization.
Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards
In this work, we study the performance of the Thompson Sampling algorithm for Contextual Bandit problems based on the framework introduced by Neu et al. and their concept of lifted information ratio.
More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime-validity
Firstly, for losses with a bounded range, we recover a strengthened version of Catoni's bound that holds uniformly for all parameter values.
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
We consider a different lower bound on the MI consisting of an entropy and a reconstruction term (ER), and analyze the main MVSSL families through its lens.
Chained Information-Theoretic bounds and Tight Regret Rate for Linear Bandit Problems
This paper studies the Bayesian regret of a variant of the Thompson-Sampling algorithm for bandit problems.
A note on generalization bounds for losses with finite moments
Moreover, the paper derives a high-probability PAC-Bayes bound for losses with a bounded variance.
