Publications

Thompson sampling for linear quadratic mean-field teams

Mukul Gagrani

Sagar Sudhakara

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

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

2021-12-12

NeurIPS.cc/2021/Workshop/DeepRL (accepted)

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

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

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

Endocytic proteins with prion-like domains form viscoelastic condensates that enable membrane remodeling

Louis-Philippe Bergeron-Sandoval

Sandeep Kumar

Hossein Khadivi Heris

Catherine L. A. Chang

Caitlin E. Cornell

Sarah L. Keller

Paul François

Adam G. Hendricks

Allen J. Ehrlicher

Rohit V. Pappu

Stephen W. Michnick

The uptake of molecules into cells, known as endocytosis, requires membrane invagination and the formation of vesicles. A version of endocyt… (see more)osis that is independent of actin polymerization is aided by the assembly of membraneless biomolecular condensates at the site of membrane invagination. Here, we show that endocytic condensates are viscoelastic bodies that concentrate key proteins with prion-like domains to enable membrane remodeling. A distinct molecular grammar, namely the preference for glutamine versus asparagine residues, underlies the cohesive interactions that give rise to endocytic condensates. We incorporate material properties inferred using active rheology into a mechanical model to explain how cohesive interactions within condensates and interfacial tensions among condensates, membranes, and the cytosol can drive membrane invagination to initiate endocyosis.

2021-12-08

Proceedings of the National Academy of Sciences of the United States of America (published)

doi.org

Adversarial Feature Desensitization

Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can … (see more)drastically impair the network's performance. Many defense methods have been proposed for improving robustness of deep networks by training them on adversarially perturbed inputs. However, these models often remain vulnerable to new types of attacks not seen during training, and even to slightly stronger versions of previously seen attacks. In this work, we propose a novel approach to adversarial robustness, which builds upon the insights from the domain adaptation field. Our method, called Adversarial Feature Desensitization (AFD), aims at learning features that are invariant towards adversarial perturbations of the inputs. This is achieved through a game where we learn features that are both predictive and robust (insensitive to adversarial attacks), i.e. cannot be used to discriminate between natural and adversarial data. Empirical results on several benchmarks demonstrate the effectiveness of the proposed approach against a wide range of attack types and attack strengths. Our code is available at https://github.com/BashivanLab/afd.

2021-12-06

Conference on Neural Information Processing Systems (Accept (Poster))

doi.org

openreview.net

Venture Scientist Bootcamp

AI Policy Compass

Supervision Requests

Publications

Venture Scientist Bootcamp

AI Policy Compass

Supervision Requests

Popular keywords:

Publications