Publications

Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
Chinnadhurai Sankar
Sandeep Subramanian
Christopher Pal
Sarath Chandar
Yoshua Bengio
Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily ad… (see more)apted to new domains, and require minimal domain engineering. A common criticism of these systems is that they seldom understand or use the available dialog history effectively. In this paper, we take an empirical approach to understanding how these models use the available dialog history by studying the sensitivity of the models to artificially introduced unnatural changes or perturbations to their context at test time. We experiment with 10 different types of perturbations on 4 multi-turn dialog datasets and find that commonly used neural dialog architectures like recurrent and transformer-based seq2seq models are rarely sensitive to most perturbations such as missing or reordering utterances, shuffling words, etc. Also, by open-sourcing our code, we believe that it will serve as a useful diagnostic tool for evaluating dialog systems in the future.
2019-06-30
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (published)
doi.org
arxiv.org
Adversarial Computation of Optimal Transport Maps
Jacob Leygonie
Jennifer She*
Amjad Almahairi
Sai Rajeswar
Aaron Courville
Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport (OT). G… (see more)enerative adversarial networks (GANs) are powerful generative models which have been successfully applied to learn maps across high-dimensional domains. However, little is known about the nature of the map learned with a GAN objective. To address this problem, we propose a generative adversarial model in which the discriminator's objective is the
2019-06-23
ArXiv (preprint)
arxiv.org
arxiv.org
Investigating Biases in Textual Entailment Datasets
Shawn Tan
Yikang Shen
Chin-wei Huang
Aaron Courville
The ability to understand logical relationships between sentences is an important task in language understanding. To aid in progress for thi… (see more)s task, researchers have collected datasets for machine learning and evaluation of current systems. However, like in the crowdsourced Visual Question Answering (VQA) task, some biases in the data inevitably occur. In our experiments, we find that performing classification on just the hypotheses on the SNLI dataset yields an accuracy of 64%. We analyze the bias extent in the SNLI and the MultiNLI dataset, discuss its implication, and propose a simple method to reduce the biases in the datasets.
2019-06-22
ArXiv (preprint)
arxiv.org
arxiv.org
Information matrices and generalization
Valentin Thomas
Fabian Pedregosa
Bart Van Merriënboer
Pierre-Antoine Manzagol
Yoshua Bengio
Nicolas Roux
This work revisits the use of information criteria to characterize the generalization of deep learning models. In particular, we empirically… (see more) demonstrate the effectiveness of the Takeuchi information criterion (TIC), an extension of the Akaike information criterion (AIC) for misspecified models, in estimating the generalization gap, shedding light on why quantities such as the number of parameters cannot quantify generalization. The TIC depends on both the Hessian of the loss H and the covariance of the gradients C. By exploring the similarities and differences between these two matrices as well as the Fisher information matrix F, we study the interplay between noise and curvature in deep models. We also address the question of whether C is a reasonable approximation to F, as is commonly assumed.
2019-06-17
arXiv.org (preprint)
dblp.uni-trier.de
Anomaly Detection with Joint Representation Learning of Content and Connection
Junhao Wang
Renhao Wang
Aayushi Kulshrestha
Reihaneh Rabbany
Social media sites are becoming a key factor in politics. These platforms are easy to manipulate for the purpose of distorting information s… (see more)pace to confuse and distract voters. Past works to identify disruptive patterns are mostly focused on analyzing the content of tweets. In this study, we jointly embed the information from both user posted content as well as a user's follower network, to detect groups of densely connected users in an unsupervised fashion. We then investigate these dense sub-blocks of users to flag anomalous behavior. In our experiments, we study the tweets related to the upcoming 2019 Canadian Elections, and observe a set of densely-connected users engaging in local politics in different provinces, and exhibiting troll-like behavior.
2019-06-15
ArXiv (preprint)
arxiv.org
arxiv.org
Conditional Computation for Continual Learning
Min Lin
Jie Fu
Yoshua Bengio
Catastrophic forgetting of connectionist neural networks is caused by the global sharing of parameters among all training examples. In this … (see more)study, we analyze parameter sharing under the conditional computation framework where the parameters of a neural network are conditioned on each input example. At one extreme, if each input example uses a disjoint set of parameters, there is no sharing of parameters thus no catastrophic forgetting. At the other extreme, if the parameters are the same for every example, it reduces to the conventional neural network. We then introduce a clipped version of maxout networks which lies in the middle, i.e. parameters are shared partially among examples. Based on the parameter sharing analysis, we can locate a limited set of examples that are interfered when learning a new example. We propose to perform rehearsal on this set to prevent forgetting, which is termed as conditional rehearsal. Finally, we demonstrate the effectiveness of the proposed method in an online non-stationary setup, where updates are made after each new example and the distribution of the received example shifts over time.
2019-06-15
ArXiv (preprint)
arxiv.org
arxiv.org
Learning the Arrow of Time
Nasim Rahaman
Steffen Wolf
Anirudh Goyal
Roman Remme
Yoshua Bengio
We humans seem to have an innate understanding of the asymmetric progression of time, which we use to efficiently and safely perceive and ma… (see more)nipulate our environment. Drawing inspiration from that, we address the problem of learning an arrow of time in a Markov (Decision) Process. We illustrate how a learned arrow of time can capture meaningful information about the environment, which in turn can be used to measure reachability, detect side-effects and to obtain an intrinsic reward signal. We show empirical results on a selection of discrete and continuous environments, and demonstrate for a class of stochastic processes that the learned arrow of time agrees reasonably well with a known notion of an arrow of time given by the celebrated Jordan-Kinderlehrer-Otto result.
2019-06-11
OpenReview.net/Anonymous_Preprint (unknown)
openreview.net
openreview.net
Learning Powerful Policies by Using Consistent Dynamics Model
Shagun Sodhani
Anirudh Goyal
Tristan Deleu
Yoshua Bengio
Sergey Levine
Jian Tang
Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models i… (see more)n RL has been made by learning models via supervised learning. But traditional model-based approaches lead to `compounding errors' when the model is unrolled step by step. Essentially, the state transitions that the learner predicts (by unrolling the model for multiple steps) and the state transitions that the learner experiences (by acting in the environment) may not be consistent. There is enough evidence that humans build a model of the environment, not only by observing the environment but also by interacting with the environment. Interaction with the environment allows humans to carry out experiments: taking actions that help uncover true causal relationships which can be used for building better dynamics models. Analogously, we would expect such interactions to be helpful for a learning agent while learning to model the environment dynamics. In this paper, we build upon this intuition by using an auxiliary cost function to ensure consistency between what the agent observes (by acting in the real world) and what it imagines (by acting in the `learned' world). We consider several tasks - Mujoco based control tasks and Atari games - and show that the proposed approach helps to train powerful policies and better dynamics models.
2019-06-10
ArXiv (preprint)
arxiv.org
arxiv.org
Note on the bias and variance of variational inference
Chin-wei Huang
Aaron Courville
In this note, we study the relationship between the variational gap and the variance of the (log) likelihood ratio. We show that the gap can… (see more) be upper bounded by some form of dispersion measure of the likelihood ratio, which suggests the bias of variational inference can be reduced by making the distribution of the likelihood ratio more concentrated, such as via averaging and variance reduction.
2019-06-08
ArXiv (preprint)
arxiv.org
arxiv.org
Dissociating memory accessibility and precision in forgetting
Sam C. Berens
Blake A. Richards
Aidan J. Horner
2019-06-03
Nature Human Behaviour (published)
doi.org
Learning Domain Randomization Distributions for Transfer of Locomotion Policies
Melissa Mozian
Juan Higuera
David Meger
Gregory Dudek
Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot sy… (see more)stem are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of success stories typically use real world data in order to carefully select the DR distribution, or incorporate real world trajectories to better estimate appropriate randomization distributions. In this paper, we consider the problem of finding good domain randomization parameters for simulation, without prior access to data from the target system. We explore the use of gradient-based search methods to learn a domain randomization with the following properties: 1) The trained policy should be successful in environments sampled from the domain randomization distribution 2) The domain randomization distribution should be wide enough so that the experience similar to the target robot system is observed during training, while addressing the practicality of training finite capacity models. These two properties aim to ensure the trajectories encountered in the target system are close to those observed during training, as existing methods in machine learning are better suited for interpolation than extrapolation. We show how adapting the domain randomization distribution while training context-conditioned policies results in improvements on jump-start and asymptotic performance when transferring a learned policy to the target environment.
2019-06-01
ArXiv (preprint)
arxiv.org
arxiv.org
Dynamic spectrum access under partial observations: A restless bandit approach
Nima Akbarzadeh
Aditya Mahajan
We consider a communication system where multiple unknown channels are available for transmission. Each channel is a channel with state whic… (see more)h evolves in a Markov manner. The transmitter has to select L channels to use and also decide the resources (e.g., power, rate, etc.) to use for each of the selected channels. It observes the state of the channels it uses and receives no feedback on the state of the other channels. We model this problem as a partially observable Markov decision process and obtain a simplified belief state. We show that the optimal resource allocation policy can be identified in closed form. Once the optimal resource allocation policy is fixed, choosing the channel scheduling policy may be viewed as a restless bandit. We present an efficient algorithm to check indexability and compute the Whittle index for each channel. When the model is indexable, the Whittle index policy, which transmits over the L channels with the smallest Whittle indices, is an attractive heuristic policy.
2019-05-31
Canadian Workshop on Information Theory (published)
doi.org