Publication
Optimal Adversarial Policies in the Multiplicative Learning System With a Malicious Expert
Related publications (44)
End-to-End Learning for Stochastic Optimization: A Bayesian Perspective
Daniel Kuhn, Yves Rychener, Tobias Sutter
We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this an ...
2023A new age in protein design empowered by deep learning
Bruno Emanuel Ferreira De Sousa Correia, Michael Bronstein, Hamed Khakzad, Casper Alexander Goverde, Arne Schneuing, Ilia Igashov
The rapid progress in the field of deep learning has had a significant impact on protein design. Deep learning methods have recently produced a breakthrough in protein structure prediction, leading to the availability of high-quality models for millions of ...
Cambridge2023A generic diffusion-based approach for 3D human pose prediction in the wild
Alexandre Massoud Alahi, Saeed Saadatnejad, Taylor Ferdinand Mordan
Predicting 3D human poses in real-world scenarios, also known as human pose forecasting, is inevitably subject to noisy inputs arising from inaccurate 3D pose estimations and occlusions. To address these challenges, we propose a diffusion-based approach th ...
IEEE2023Optimal recovery of unsecured debt via interpretable reinforcement learning
Thomas Alois Weber, Michael Mark, Huanxi Liu
This paper addresses the issue of interpretability and auditability of reinforcement-learning agents employed in the recovery of unsecured consumer debt. To this end, we develop a deterministic policy-gradient method that allows for a natural integration o ...
2022Personalized Productive Engagement Recognition in Robot-Mediated Collaborative Learning
Barbara Bruno, Jauwairia Nasir
In this paper, we propose and compare personalized models for Productive Engagement (PE) recognition. PE is defined as the level of engagement that maximizes learning. Previously, in the context of robot-mediated collaborative learning, a framework of prod ...
2022An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
Rachid Guerraoui, Sadegh Farhadkhani, Oscar Jean Olivier Villemaud, Le Nguyen Hoang
To study the resilience of distributed learning, the “Byzantine" literature considers a strong threat model where workers can report arbitrary gradients to the parameter server. Whereas this model helped obtain several fundamental results, it has sometimes ...
PMLR2022Are socially-aware trajectory prediction models really socially-aware?
Alexandre Massoud Alahi, Seyed Mohsen Moosavi Dezfooli, Saeed Saadatnejad, Mohammadhossein Bahari, Pedram Khorsandi
Our transportation field has recently witnessed an arms race of neural network-based trajectory predictors. While these predictors are at the core of many applications such as autonomous navigation or pedestrian flow simulations, their adversarial robustne ...
2022Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates
Ali H. Sayed, Kun Yuan, Lucas Cesar Eduardo Cassano
This article develops a fully decentralized multiagent algorithm for policy evaluation. The proposed scheme can be applied to two distinct scenarios. In the first scenario, a collection of agents have distinct datasets gathered by following different behav ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021Surprise-based model estimation in reinforcement learning: algorithms and brain signatures
Learning how to act and adapting to unexpected changes are remarkable capabilities of humans and other animals. In the absence of a direct recipe to follow in life, behaviour is often guided by rewarding and by surprising events. A positive or a negative o ...
EPFL2021Exploring policy change through agent-based simulation
Policymaking is a complex process that has been studied using policy process theories almost exclusively. These theories have been built using a large number of qualitative cases. Such methods are useful for theory building but remain limited for theory ex ...
EPFL2021