Publications

Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference

Matthew D Riemer

Ignacio Cases

Robert Ajemian

Miao Liu

Irina Rish

Yuhai Tu

Gerald Tesauro

Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neura… (see more)l network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples. We then propose a new algorithm, Meta-Experience Replay (MER), that directly exploits this view by combining experience replay with optimization based meta-learning. This method learns parameters that make interference based on future gradients less likely and transfer based on future gradients more likely. We conduct experiments across continual lifelong supervised learning benchmarks and non-stationary reinforcement learning environments demonstrating that our approach consistently outperforms recently proposed baselines for continual learning. Our experiments show that the gap between the performance of MER and baseline algorithms grows both as the environment gets more non-stationary and as the fraction of the total experiences stored gets smaller.

2019-01-01

ICLR.cc/2019/Conference (poster)

LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models

Yuanshuo Zhou

Bradley Gram-Hansen

Tobias Kohn

Tom Rainforth

Hongseok Yang

F. Wood

We develop a new Low-level, First-order Probabilistic Programming Language~(LF-PPL) suited for models containing a mix of continuous, discre… (see more)te, and/or piecewise-continuous variables. The key success of this language and its compilation scheme is in its ability to automatically distinguish parameters the density function is discontinuous with respect to, while further providing runtime checks for boundary crossings. This enables the introduction of new inference engines that are able to exploit gradient information, while remaining efficient for models which are not everywhere differentiable. We demonstrate this ability by incorporating a discontinuous Hamiltonian Monte Carlo (DHMC) inference engine that is able to deliver automated and efficient inference for non-differentiable models. Our system is backed up by a mathematical formalism that ensures that any model expressed in this language has a density with measure zero discontinuities to maintain the validity of the inference engine.

2019-01-01

AISTATS (published)

proceedings.mlr.press

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

Kundan Kumar

Rithesh Kumar

Thibault De Boissière

Lucas Gestin

Wei Zhen Teoh

Jose Sotelo

Alexandre De Brébisson

Yoshua Bengio

Neural Multisensory Scene Inference

Jae Hyun Lim

Pedro O. Pinheiro

Negar Rostamzadeh

Chris Pal

Sungjin Ahn

For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine multisensory … (see more)cues from numerous trials, e.g., by looking at and touching objects. Despite its importance, multisensory 3D scene representation learning has received less attention compared to the unimodal setting. In this paper, we propose the Generative Multisensory Network (GMN) for learning latent representations of 3D scenes which are partially observable through multiple sensory modalities. We also introduce a novel method, called the Amortized Product-of-Experts, to improve the computational efficiency and the robustness to unseen combinations of modalities at test time. Experimental results demonstrate that the proposed model can efficiently infer robust modality-invariant 3D-scene representations from arbitrary combinations of modalities and perform accurate cross-modal generation. To perform this exploration we have also developed a novel multi-sensory simulation environment for embodied agents.

Ordered Memory

Yikang Shen

Shawn Tan

Arian Hosseini

Zhouhan Lin

Alessandro Sordoni

Stack-augmented recurrent neural networks (RNNs) have been of interest to the deep learning community for some time. However, the difficult… (see more)y of training memory models remains a problem obstructing the widespread use of such models. In this paper, we propose the Ordered Memory architecture. Inspired by Ordered Neurons (Shen et al., 2018), we introduce a new attention-based mechanism and use its cumulative probability to control the writing and erasing operation of the memory. We also introduce a new Gated Recursive Cell to compose lower-level representations into higher-level representation. We demonstrate that our model achieves strong performance on the logical inference task (Bowman et al., 2015) and the ListOps (Nangia and Bowman, 2018) task. We can also interpret the model to retrieve the induced tree structure, and find that these induced structures align with the ground truth. Finally, we evaluate our model on the Stanford Sentiment Treebank tasks (Socher et al., 2013), and find that it performs comparatively with the state-of-the-art methods in the literature.

Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks

Yikang Shen

Shawn Tan

Alessandro Sordoni

Natural language is hierarchically structured: smaller units (e.g., phrases) are nested within larger units (e.g., clauses). When a larger c… (see more)onstituent ends, all of the smaller constituents that are nested within it must also be closed. While the standard LSTM architecture allows different neurons to track information at different time scales, it does not have an explicit bias towards modeling a hierarchy of constituents. This paper proposes to add such an inductive bias by ordering the neurons; a vector of master input and forget gates ensures that when a given neuron is updated, all the neurons that follow it in the ordering are also updated. Our novel recurrent architecture, ordered neurons LSTM (ON-LSTM), achieves good performance on four different tasks: language modeling, unsupervised parsing, targeted syntactic evaluation, and logical inference.

2019-01-01

ICLR.cc/2019/Conference (oral)

No Press Diplomacy: Modeling Multi-Agent Gameplay

Philip Paquette

Yuchen Lu

Steven Bocco

Max Olan Smith

satya ortiz gagne

Jonathan K. Kummerfeld

Satinder Singh

Joelle Pineau

Probability Distillation: A Caveat and Alternatives

Chin-Wei Huang

Faruk Ahmed

Kundan Kumar

Alexandre Lacoste

Due to Van den Oord et al. (2018), probability distillation has recently been of interest to deep learning practitioners, where, as a practi… (see more)cal workaround for deploying autoregressive models in real-time applications, a student network is used to obtain quality samples in parallel. We identify a pathological optimization issue with the adopted stochastic minimization of the reverse-KL divergence: the curse of dimensionality results in a skewed gradient distribution that renders training inefﬁcient. This means that KL-based “evaluative” training can be susceptible to poor exploration if the target distribution is highly structured. We then explore alternative principles for distillation, including one with an “instructive” signal, and show that it is possible to achieve qualitatively better results than with KL minimization.

2019-01-01

Conference on Uncertainty in Artificial Intelligence (published)

proceedings.mlr.press

Quaternion Recurrent Neural Networks

Titouan Parcollet

Mirco Ravanelli

Mohamed Morchid

Georges Linarès

Chiheb Trabelsi

Renato De Mori

Yoshua Bengio

Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term d… (see more)ependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or images recognition, involve multi-dimensional input features that are characterized by strong internal dependencies between the dimensions of the input vector. We propose a novel quaternion recurrent neural network (QRNN), alongside with a quaternion long-short term memory neural network (QLSTM), that take into account both the external relations and these internal structural dependencies with the quaternion algebra. Similarly to capsules, quaternions allow the QRNN to code internal dependencies by composing and processing multidimensional features as single entities, while the recurrent operation reveals correlations between the elements composing the sequence. We show that both QRNN and QLSTM achieve better performances than RNN and LSTM in a realistic application of automatic speech recognition. Finally, we show that QRNN and QLSTM reduce by a maximum factor of 3.3x the number of free parameters needed, compared to real-valued RNNs and LSTMs to reach better results, leading to a more compact representation of the relevant information.

2019-01-01

ICLR.cc/2019/Conference (poster)

Real-Time Reinforcement Learning

Simon Ramstedt

Chris Pal

Recall Traces: Backtracking Models for Efficient Reinforcement Learning

Anirudh Goyal

Philemon Brakel

William Fedus

Soumye Singhal

Timothy P. Lillicrap

Sergey Levine

Hugo Larochelle

Yoshua Bengio

In many environments only a tiny subset of all states yield high reward. In these cases, few of the interactions with the environment provid… (see more)e a relevant learning signal. Hence, we may want to preferentially train on those high-reward states and the probable trajectories leading to them. To this end, we advocate for the use of a backtracking model that predicts the preceding states that terminate at a given high-reward state. We can train a model which, starting from a high value state (or one that is estimated to have high value), predicts and sample for which the (state, action)-tuples may have led to that high value state. These traces of (state, action) pairs, which we refer to as Recall Traces, sampled from this backtracking model starting from a high value state, are informative as they terminate in good states, and hence we can use these traces to improve a policy. We provide a variational interpretation for this idea and a practical algorithm in which the backtracking model samples from an approximate posterior distribution over trajectories which lead to large rewards. Our method improves the sample efficiency of both on- and off-policy RL algorithms across several environments and tasks.

2019-01-01

ICLR.cc/2019/Conference (poster)