152 citations
- Carnegie Mellon UniversityUS5 papers
- Ludwig-Maximilians-Universität MünchenDE5 papers
- Center for Strategic ResearchRU4 papers
- Robotic Research (United States)US4 papers
- LMU KlinikumDE3 papers
- Optim Design (United States)US3 papers
- Aalborg UniversityDK2 papers
- Centre for Arctic Gas Hydrate, Environment and ClimateNO2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Columbia UniversityUS2 papers
- Stanford UniversityUS2 papers
- UiT The Arctic University of NorwayNO2 papers
15 papers · 1 filter
Bayesian policy gradient and actor-critic algorithms
Mohammad Ghavamzadeh, Yaakov Engel, Michal Valko
Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods u…
EmbedOR: Provable Cluster-Preserving Visualizations with Curvature-Based Stochastic Neighbor Embeddings
Tristan Luca Saidi, Abigail Hickok, Bastian Rieck +1
Stochastic Neighbor Embedding (SNE) algorithms like UMAP and tSNE often produce visualizations that do not preserve the geometry of noisy and high dimensional data. In particular,…
SHAining on Process Mining: Explaining Event Log Characteristics Impact on Algorithms
Andrea Maldonado, Christian M. M. Frey, Sai Anirudh Aryasomayajula +3
Process mining aims to extract and analyze insights from event logs, yet algorithm metric results vary widely depending on structural event log characteristics. Existing work often…
Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation
Adrian Hill, Guillaume Dalle
From implicit differentiation to probabilistic modeling, Jacobian and Hessian matrices have many potential use cases in Machine Learning (ML), but they are viewed as computationall…
On Cold Posteriors of Probabilistic Neural Networks: Understanding the Cold Posterior Effect and A New Way to Learn Cold Posteriors with Tight Generalization Guarantees
Yijie Zhang
Bayesian inference provides a principled probabilistic framework for quantifying uncertainty by updating beliefs based on prior knowledge and observed data through Bayes' theorem.…
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
Youssef Allouah, Abdellah El Mrini, Rachid Guerraoui +2
Federated learning (FL) is an appealing paradigm that allows a group of machines (a.k.a. clients) to learn collectively while keeping their data local. However, due to the heteroge…