Joelle Pineau

Streaming kernel regression with provably adaptive mean, variance, and regularization

Audrey Durand

Odalric-Ambrym Maillard

We consider the problem of streaming kernel regression, when the observations arrive sequentially and the goal is to recover the underlying … (see more)mean function, assumed to belong to an RKHS. The variance of the noise is not assumed to be known. In this context, we tackle the problem of tuning the regularization parameter adaptively at each time step, while maintaining tight confidence bounds estimates on the value of the mean function at each point. To this end, we first generalize existing results for finite-dimensional linear regression with fixed regularization and known variance to the kernel setup with a regularization parameter allowed to be a measurable function of past observations. Then, using appropriate self-normalized inequalities we build upper and lower bound estimates for the variance, leading to Bersntein-like concentration bounds. The later is used in order to define the adaptive regularization. The bounds resulting from our technique are valid uniformly over all observation points and all time steps, and are compared against the literature with numerical experiments. Finally, the potential of these tools is illustrated by an application to kernelized bandits, where we revisit the Kernel UCB and Kernel Thompson Sampling procedures, and show the benefits of the novel adaptive kernel tuning strategy.

2017-12-31

Journal of Machine Learning Research (published)

Temporal Regularization for Markov Decision Process

Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensiona… (see more)l domains. Regularization is a commonly used technique in machine learning to reduce variance, at the cost of introducing some bias. Most existing regularization techniques focus on spatial (perceptual) regularization. Yet in reinforcement learning, due to the nature of the Bellman equation, there is an opportunity to also exploit temporal regularization based on smoothness in value estimates over trajectories. This paper explores a class of methods for temporal regularization. We formally characterize the bias induced by this technique using Markov chain concepts. We illustrate the various characteristics of temporal regularization via a sequence of simple discrete and continuous MDPs, and show that the technique provides improvement even in high-dimensional Atari games.

2017-12-31

Advances in Neural Information Processing Systems 31 (NeurIPS 2018) (published)

dblp.uni-trier.de

Tensor Regression Networks with various Low-Rank Tensor Approximations

Xingwei Cao

Guillaume Rabusseau

Tensor regression networks achieve high compression rate of neural networks while having slight impact on performances. They do so by imposi… (see more)ng low tensor rank structure on the weight matrices of fully connected layers. In recent years, tensor regression networks have been investigated from the perspective of their compressive power, however, the regularization effect of enforcing low-rank tensor structure has not been investigated enough. We study tensor regression networks using various low-rank tensor approximations, aiming to compare the compressive and regularization power of different low-rank constraints. We evaluate the compressive and regularization performances of the proposed model with both deep and shallow convolutional neural networks. The outcome of our experiment suggests the superiority of Global Average Pooling Layer over Tensor Regression Layer when applied to deep convolutional neural network with CIFAR-10 dataset. On the contrary, shallow convolutional neural networks with tensor regression layer and dropout achieved lower test error than both Global Average Pooling and fully-connected layer with dropout function when trained with a small number of samples.

2017-12-26

ArXiv (preprint)

Actual: Actor-Critic Under Adversarial Learning

Nan Rosemary Ke

R Devon Hjelm

Generative Adversarial Networks (GANs) are a powerful framework for deep generative modeling. Posed as a two-player minimax problem, GANs ar… (see more)e typically trained end-to-end on real-valued data and can be used to train a generator of high-dimensional and realistic images. However, a major limitation of GANs is that training relies on passing gradients from the discriminator through the generator via back-propagation. This makes it fundamentally difficult to train GANs with discrete data, as generation in this case typically involves a non-differentiable function. These difficulties extend to the reinforcement learning setting when the action space is composed of discrete decisions. We address these issues by reframing the GAN framework so that the generator is no longer trained using gradients through the discriminator, but is instead trained using a learned critic in the actor-critic framework with a Temporal Difference (TD) objective. This is a natural fit for sequence modeling and we use it to achieve improvements on language modeling tasks over the standard Teacher-Forcing methods.

2017-11-12

ArXiv (preprint)

A Deep Reinforcement Learning Chatbot

Iulian V. Serban

Mathieu Germain

Michael Pieper

Nan Rosemary Ke

Sai Mudumba

Alexandre De Brébisson

Jose M. R. Sotelo

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon … (see more)Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than many competing systems. Due to its machine learning architecture, the system is likely to improve with additional data.

2017-09-06

ArXiv (preprint)

Predicting Success in Goal-Driven Human-Human Dialogues

Michael Noseworthy

Jackie CK Cheung

In goal-driven dialogue systems, success is often defined based on a structured definition of the goal. This requires that the dialogue syst… (see more)em be constrained to handle a specific class of goals and that there be a mechanism to measure success with respect to that goal. However, in many human-human dialogues the diversity of goals makes it infeasible to define success in such a way. To address this scenario, we consider the task of automatically predicting success in goal-driven human-human dialogues using only the information communicated between participants in the form of text. We build a dataset from stackoverflow.com which consists of exchanges between two users in the technical domain where ground-truth success labels are available. We then propose a turn-based hierarchical neural network model that can be used to predict success without requiring a structured goal definition. We show this model outperforms rule-based heuristics and other baselines as it is able to detect patterns over the course of a dialogue and capture notions such as gratitude.

2017-07-31

SIGDIAL Conference (published)

Multi-Modal Variational Encoder-Decoders

Iulian V. Serban

Alexander G. Ororbia II

Aaron Courville

2017-04-23

arXiv.org (preprint)

openreview.net

A Sparse Probabilistic Model of User Preference Data

Matthew J. A. Smith

Laurent Charlin

2017-04-10

Advances in Artificial Intelligence (published)

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

Iulian V. Serban

Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterance… (see more)s in a dialogue. In an effort to model this kind of generative process, we propose a neural network-based generative architecture, with latent stochastic variables that span a variable number of time steps. We apply the proposed model to the task of dialogue response generation and compare it with recent neural network architectures. We evaluate the model performance through automatic evaluation metrics and by carrying out a human evaluation. The experiments demonstrate that our model improves upon recently proposed models and that the latent variables facilitate the generation of long outputs and maintain the context.

2017-02-11

Proceedings of the AAAI Conference on Artificial Intelligence (published)

Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus

Iulian Vlad Serban

Chia-Wei Liu

In this paper, we construct and train end-to-end neural network-based dialogue systems usingan updated version of the recent Ubuntu Dialogue… (see more) Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This dataset is interesting because of its size, long context lengths, and technical nature; thus, it can be used to train large models directly from data with minimal feature engineering, which can be both time consuming and expensive. We provide baselines in two different environments: one where models are trained to maximize the log-likelihood of a generated utterance conditioned on the context of the conversation, and one where models are trained to select the correct next response from a list of candidate responses. These are both evaluated on a recall task that we call Next Utterance Classification (NUC), as well as other generation-specific metrics. Finally, we provide a qualitative error analysis to help determine the most promising directions for future research on the Ubuntu Dialogue Corpus, and for end-to-end dialogue systems in general.

2017-01-19

Dialogue & Discourse (published)

An Actor-Critic Algorithm for Sequence Prediction

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Curren… (see more)t log-likelihood training methods are limited by the discrepancy between their training and testing modes, as models must generate tokens conditioned on their previous guesses rather than the ground-truth tokens. We address this problem by introducing a \textit{critic} network that is trained to predict the value of an output token, given the policy of an \textit{actor} network. This results in a training procedure that is much closer to the test phase, and allows us to directly optimize for a task-specific score such as BLEU. Crucially, since we leverage these techniques in the supervised learning setting rather than the traditional RL setting, we condition the critic network on the ground-truth output. We show that our method leads to improved performance on both a synthetic task, and for German-English machine translation. Our analysis paves the way for such methods to be applied in natural language generation tasks, such as machine translation, caption generation, and dialogue modelling.

2016-12-31

ICLR.cc/2017/conference (poster)