Publications

Decision Referrals in Human-Automation Teams
Kesav Kaza
Jerome Le Ny
Aditya Mahajan
We consider a model for optimal decision referrals in human-automation teams performing binary classification tasks. The automation observes… (see more) a batch of independent tasks, analyzes them, and has the option to refer a subset of them to a human operator. The human operator performs fresh analysis of the tasks referred to him. Our key modeling assumption is that the human performance degrades with workload (i.e., the number of tasks referred to human). We model the problem as a stochastic optimization problem. We first consider the special case when the workload of the human is pre-specified. We show that in this setting it is optimal to myopically refer tasks which lead to the largest reduction in the conditional expected cost until the desired workload target is met. We next consider the general setting where there is no constraint on the workload. We leverage the solution of the previous step and provide a search algorithm to efficiently find the optimal set of tasks to refer. Finally, we present a numerical study to compare the performance of our algorithm with some baseline allocation policies.
2021-12-13
IEEE Conference on Decision and Control (published)
doi.org
Mean-field approximation for large-population beauty-contest games
Raihan Seraj
Jerome Le Ny
Aditya Mahajan
We study a class of Keynesian beauty contest games where a large number of heterogeneous players attempt to estimate a common parameter base… (see more)d on their own observations. The players are rewarded for producing an estimate close to a certain multiplicative factor of the average decision, this factor being specific to each player. This model is motivated by scenarios arising in commodity or financial markets, where investment decisions are sometimes partly based on following a trend. We provide a method to compute Nash equilibria within the class of affine strategies. We then develop a mean-field approximation, in the limit of an infinite number of players, which has the advantage that computing the best-response strategies only requires the knowledge of the parameter distribution of the players, rather than their actual parameters. We show that the mean-field strategies lead to an ε-Nash equilibrium for a system with a finite number of players. We conclude by analyzing the impact on individual behavior of changes in aggregate population behavior.
2021-12-13
IEEE Conference on Decision and Control (published)
doi.org
Thompson sampling for linear quadratic mean-field teams
Mukul Gagrani
Sagar Sudhakara
Aditya Mahajan
Ashutosh Nayyar
Yi Ouyang
We consider optimal control of an unknown multi-agent linear quadratic (LQ) system where the dynamics and the cost are coupled across the ag… (see more)ents through the mean-field (i.e., empirical mean) of the states and controls. Directly using single-agent LQ learning algorithms in such models results in regret which increases polynomially with the number of agents. We propose a new Thompson sampling based learning algorithm which exploits the structure of the system model and show that the expected Bayesian regret of our proposed algorithm for a system with agents of |M| different types at time horizon T is
2021-12-13
2021 60th IEEE Conference on Decision and Control (CDC) (published)
doi.org
arxiv.org
Behavior Predictive Representations for Generalization in Reinforcement Learning
Siddhant Agarwal
Aaron Courville
Rishabh Agarwal
Deep reinforcement learning (RL) agents trained on a few environments, often struggle to generalize on unseen environments, even when such e… (see more)nvironments are semantically equivalent to training environments. Such agents learn representations that overfit the characteristics of the training environments. We posit that generalization can be improved by assigning similar representations to scenarios with similar sequences of long-term optimal behavior. To do so, we propose behavior predictive representations (BPR) that capture long-term optimal behavior. BPR trains an agent to predict latent state representations multiple steps into the future such that these representations can predict the optimal behavior at the future steps. We demonstrate that BPR provides large gains on a jumping task from pixels, a problem designed to test generalization.
2021-12-12
NeurIPS.cc/2021/Workshop/DeepRL (accepted)
openreview.net
openreview.net
Early Transcriptional Changes in Rabies Virus-Infected Neurons and Their Impact on Neuronal Functions
Seonhee Kim
Florence Larrous
Hugo Varet
Rachel Legendre
Lena Feige
Guillaume Dumas
Rebecca Matsas
Georgia Kouroupi
Regis Grailhe
Hervé Bourhy
Rabies is a zoonotic disease caused by rabies virus (RABV). As rabies advances, patients develop a variety of severe neurological symptoms t… (see more)hat inevitably lead to coma and death. Unlike other neurotropic viruses that can induce symptoms of a similar range, RABV-infected post-mortem brains do not show significant signs of inflammation nor the structural damages on neurons. This suggests that the observed neurological symptoms possibly originate from dysfunctions of neurons. However, many aspects of neuronal dysfunctions in the context of RABV infection are only partially understood, and therefore require further investigation. In this study, we used differentiated neurons to characterize the RABV-induced transcriptomic changes at the early time-points of infection. We found that the genes modulated in response to the infection are particularly involved in cell cycle, gene expression, immune response, and neuronal function-associated processes. Comparing a wild-type RABV to a mutant virus harboring altered matrix proteins, we found that the RABV matrix protein plays an important role in the early down-regulation of host genes, of which a significant number is involved in neuronal functions. The kinetics of differentially expressed genes (DEGs) are also different between the wild type and mutant virus datasets. The number of modulated genes remained constant upon wild-type RABV infection up to 24 h post-infection, but dramatically increased in the mutant condition. This result suggests that the intact viral matrix protein is important to control the size of host gene modulation. We then examined the signaling pathways previously studied in relation to the innate immune responses against RABV, and found that these pathways contribute to the changes in neuronal function-associated processes. We further examined a set of regulated genes that could impact neuronal functions collectively, and demonstrated in calcium imaging that indeed the spontaneous activity of neurons is influenced by RABV infection. Overall, our findings suggest that neuronal function-associated genes are modulated by RABV early on, potentially through the viral matrix protein-interacting signaling molecules and their downstream pathways.
2021-12-12
Frontiers in Microbiology (published)
doi.org
Long-Term Credit Assignment via Model-based Temporal Shortcuts
Michel Ma
Pierluca D'Oro
Yoshua Bengio
Pierre-Luc Bacon
2021-12-12
NeurIPS.cc/2021/Workshop/DeepRL (accepted)
openreview.net
openreview.net
A taxonomy of weight learning methods for statistical relational learning
Sriram Srinivasan
Charles Dickens
Eriq Augustine
Golnoosh Farnadi
Lise Getoor
2021-12-12
Machine-mediated learning (published)
doi.org
Interpreting Lambda Calculus in Domain-Valued Random Variables
Robert Furber
Radu Mardare
Prakash Panangaden
Douglas Scott
2021-12-11
ArXiv (preprint)
doi.org
arxiv.org
Artificial Intelligence in Surgical Education: Considerations for Interdisciplinary Collaborations
Elif Bilgic
Andrew Gorgy
Meredith Young
S. A. Rahimi
Jason M. Harley
2021-12-09
Surgical Innovation (published)
doi.org
Effect of diversity in Meta-Learning
Ramnath Kumar
Tristan Deleu
Yoshua Bengio
Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that task … (see more)distribution plays a vital role in the performance of the model. Conventional wisdom is that task diversity should improve the performance of meta-learning. In this work, we find evidence to the contrary; we study different task distributions on a myriad of models and datasets to evaluate the effect of task diversity on meta-learning algorithms. For this experiment, we train on two datasets - Omniglot and miniImageNet and with three broad classes of meta-learning models - Metric-based (i.e., Protonet, Matching Networks), Optimization-based (i.e., MAML, Reptile, and MetaOptNet), and Bayesian meta-learning models (i.e., CNAPs). Our experiments demonstrate that the effect of task diversity on all these algorithms follows a similar trend, and task diversity does not seem to offer any benefits to the learning of the model. Furthermore, we also demonstrate that even a handful of tasks, repeated over multiple batches, would be sufficient to achieve a performance similar to uniform sampling and draws into question the need for additional tasks to create better models.
2021-12-09
NeurIPS.cc/2021/Workshop/MetaLearn (poster)
openreview.net
openreview.net
Few Shot Image Generation via Implicit Autoencoding of Support Sets
Andy Huang
Kuan-Chieh Wang
Guillaume Rabusseau
Alireza Makhzani
Recent generative models such as generative adversarial networks have achieved remarkable success in generating realistic images, but they r… (see more)equire large training datasets and computational resources. The goal of few-shot image generation is to learn the distribution of a new dataset from only a handful of examples by transferring knowledge learned from structurally similar datasets. Towards achieving this goal, we propose the “Implicit Support Set Autoencoder” (ISSA) that adversarially learns the relationship across datasets using an unsupervised dataset representation, while the distribution of each individual dataset is learned using implicit distributions. Given a few examples from a new dataset, ISSA can generate new samples by inferring the representation of the underlying distribution using a single forward pass. We showcase significant gains from our method on generating high quality and diverse images for unseen classes in the Omniglot and CelebA datasets in few-shot image generation settings.
2021-12-09
NeurIPS.cc/2021/Workshop/MetaLearn (poster)
openreview.net
openreview.net
Maternal chemosignals enhance infant-adult brain-to-brain synchrony
Yaara Endevelt-Shapira
Amir Djalovski
Guillaume Dumas
Ruth Feldman
2021-12-09
Science Advances (published)
doi.org