output
20162025
most citedThe physics of higher-order interactions in complex systems

938 citations

Showing cs.LGShow all

9 papers · 1 filter

cs.LG20241 cited

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…

cs.LG2021

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…

cs.LG2021129 cited

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…

cs.LG20203 cited

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…

cs.LG202033 cited

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…

cs.LG2019162 cited

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…