Montreal

We consider the problem of making efficient use of heterogeneous training data in neural machine translation (NMT). Specifically, given a training dataset with a sentence-level feature such as noise, we seek an optimal curriculum, or order for presenting examples to the system during training. Our curriculum framework allows examples to appear an arbitrary number of times, and thus generalizes...

We present graph partition neural networks (GPNN), an extension of graph neu- ral networks (GNNs) able to handle extremely large graphs. GPNNs alternate between locally propagating information between nodes in small subgraphs and globally propagating information between the subgraphs. To efficiently partition graphs, we experiment with spectral partition and also propose a modified multi- seed...

This work revisits the notion of \textit{information criterion} to characterize generalization for modern deep learning models. In particular, we empirically demonstrate the effectiveness of the Takeuchi Information Criterion, an extension of the Akaike Information Criterion for misspecified models, in estimating the generalization gap, shedding light on why quantities such as the number of...

The past year has witnessed rapid advances in sequence-to-sequence (seq2seq) modeling for Machine Translation (MT). The classic RNN-based approaches to MT were first out-performed by the convolutional seq2seq model, which was then out-performed by the more recent Transformer model. Each of these new approaches consists of a fundamental architecture accompanied by a set of modeling and training...

In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress made in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained on episodes representing different classification problems, each with a small labeled training set and its...

While normalizing flows have led to significant advances in modeling high-dimensional continuous distributions, their applicability to discrete distributions remains unknown. In this paper, we show that flows can in fact be extended to discrete events---and under a simple change-of-variables formula not requiring log-determinant-Jacobian computations. Discrete flows have numerous applications....

We propose a new perspective on representation learning in reinforcement learning based on geometric properties of the space of value functions. We leverage this perspective to provide formal evidence regarding the usefulness of value functions as auxiliary tasks. Our formulation considers adapting the representation to minimize the (linear) approximation of the value function of all stationary...

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help \emph{exploration} by encouraging a more stochastic policy. In this work, we analyze that claim and, through new visualizations of the optimization landscape, observe that its effect matches that of a regularizer. We show that even with access to the exact gradient, policy...

We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope \cite{aigner2010proofs}. To demonstrate this result, we exhibit several properties of the structural relationship between policies and value functions including the line...

Geometry-sensitive metrics between probability distributions play an important role in distributional reinforcement learning \citep{bellemare2017distributional}. In particular, the C51 algorithm can be partially explained in terms of one such metric, the Cram\'er distance (Rowland et al., 2018). The explanation is partial, however, because C51 uses a softmax to guarantee that its output is a...