Personne
Patrick Thiran
Publications associées (161)
Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization
Bayesian Optimization (BO) is typically used to optimize an unknown function f that is noisy and costly to evaluate, by exploiting an acquisition function that must be maximized at each optimization step. Even if provably asymptotically optimal BO algorith ...
2024Leveraging Unlabeled Data to Track Memorization
Patrick Thiran, Mahsa Forouzesh, Hanie Sedghi
Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We propose a metric, ca ...
2023The power of adaptivity in source identification with time queries on the path
Patrick Thiran, Gergely Odor, Victor Cyril L Lecomte
We study the problem of identifying the source of a stochastic diffusion process spreading on a graph based on the arrival times of the diffusion at a few queried nodes. In a graph , an unknown source node is drawn uniformly at random, ...
2022On the robustness of the metric dimension of grid graphs to adding a single edge
Patrick Thiran, Gergely Odor, Satvik Mehul Mashkaria
The metric dimension (MD) of a graph is a combinatorial notion capturing the minimum number of landmark nodes needed to distinguish every pair of nodes in the graph based on graph distance. We study how much the MD can increase if we add a single edge to t ...
2022Momentum-Based Policy Gradient with Second-Order Information
Patrick Thiran, Negar Kiyavash, Mohammadsadegh Khorasani, Saber Salehkaleybar
Variance-reduced gradient estimators for policy gradient methods have been one of the main focus of research in the reinforcement learning in recent years as they allow acceleration of the estimation process. We propose a variance-reduced policy-gradient m ...
2022Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function
Patrick Thiran, Negar Kiyavash, Saber Salehkaleybar
We study the performance of Stochastic Cubic Regularized Newton (SCRN) on a class of functions satisfying gradient dominance property with which holds in a wide range of applications in machine learning and signal processing. This conditio ...
NeurIPS2022A Variational Inference Approach to Learning Multivariate Wold Processes
Patrick Thiran, Matthias Grossglauser, Negar Kiyavash, Seyed Jalal Etesami, William Trouleau
Temporal point-processes are often used for mathematical modeling of sequences of discrete events with asynchronous timestamps. We focus on a class of temporal point-process models called multivariate Wold processes (MWP). These processes are well suited t ...
PMLR2021Generalization Comparison of Deep Neural Networks via Output Sensitivity
Patrick Thiran, Farnood Salehi, Mahsa Forouzesh
Although recent works have brought some insights into the performance improvement of techniques used in state-of-the-art deep-learning models, more work is needed to understand their generalization properties. We shed light on this matter by linking the lo ...
IEEE2021War of Words II: Enriched Models of Law-Making Processes
Patrick Thiran, Matthias Grossglauser, Victor Kristof, Aswin Suresh
The European Union law-making process is an instance of a peer- production system. We mine a rich dataset of law edits and intro- duce models predicting their adoption by parliamentary committees. Edits are proposed by parliamentarians, and they can be in ...
ACM2021Disparity Between Batches as a Signal for Early Stopping
Patrick Thiran, Mahsa Forouzesh
We propose a metric for evaluating the generalization ability of deep neural networks trained with mini-batch gradient descent. Our metric, called gradient disparity, is the l2 norm distance between the gradient vectors of two mini-batches drawn from the t ...
Springer2021