938 citations
- Turing InstituteGB45 papers
- University of OxfordGB19 papers
- University College LondonGB18 papers
- Queen Mary University of LondonGB15 papers
- University of ManchesterGB14 papers
- University of WarwickGB14 papers
- University of CambridgeGB12 papers
- University of EdinburghGB9 papers
- Imperial College LondonGB8 papers
- Centre National de la Recherche ScientifiqueFR7 papers
- University of LeedsGB6 papers
- Aalto UniversityFI5 papers
9 papers · 1 filter
Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space
Sanyam Vyas, Chris Hicks, Vasilios Mavroudis
This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on…
Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski +2
Approximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has many applications acr…
SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
Chi Ian Tang, Ignacio Perez-Pozuelo, Dimitris Spathis +3
Machine learning and deep learning have shown great promise in mobile sensing applications, including Human Activity Recognition. However, the performance of such models in real-wo…
Improving Fairness and Privacy in Selection Problems
Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan +1
Supervised learning models have been increasingly used for making decisions about individuals in applications such as hiring, lending, and college admission. These models may inher…
Optimal Continual Learning has Perfect Memory and is NP-hard
Jeremias Knoblauch, Hisham Husain, Tom Diethe
Continual Learning (CL) algorithms incrementally learn a predictor or representation across multiple sequentially observed tasks. Designing CL algorithms that perform reliably and…
Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration
Meelis Kull, Miquel Perello-Nieto, Markus Kängsepp +3
Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperatu…