Guillaume Rabusseau

farzaneh.heidari@mila.quebec

Beheshteh Toloueirakhshan

Doctorat - Université de Montréal

rakhshab@mila.quebec

Farzaneh Heidari

Doctorat - Université de Montréal

Co-superviseur⋅e :

Jian Tang

Julia Gastinger

Collaborateur·rice alumni - University of Mannheim

Co-superviseur⋅e :

Reihaneh Rabbany

julia.gastinger@mila.quebec

Jun Dai

Postdoctorat - Université de Montréal

jun.dai@mila.quebec

marawan.gamal@mila.quebec

Marawan Gamal

Doctorat - Université de Montréal

michael.rizvi-martel@mila.quebec

Maude Lizaire

Doctorat - Université de Montréal

lizairem@mila.quebec

Michael Rizvi-Martel

Maîtrise recherche - Université de Montréal

Site web

Shirzadkhani Razieh Shirzadkhani

Omar Chikar

Maîtrise recherche - Université de Montréal

omar.chikhar@mila.quebec

Collaborateur·rice de recherche

Co-superviseur⋅e :

Reihaneh Rabbany

razieh.shirzadkhani@mila.quebec

soroush.omranpour@mila.quebec

Shenyang Huang

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Maîtrise recherche - McGill University

Superviseur⋅e principal⋅e :

Reihaneh Rabbany

Publications

Nonlinear Weighted Finite Automata

Tianyu Li

Doina Precup

Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models. Given the recent succ… (voir plus)esses of nonlinear models in machine learning, it is natural to wonder whether extending WFA to the nonlinear setting would be beneficial. In this paper, we propose a novel model of neural network based nonlinear WFA model (NL-WFA) along with a learning algorithm. Our learning algorithm is inspired by the spectral learning algorithm for WFA and relies on a nonlinear decomposition of the so-called Hankel matrix, by means of an auto-encoder network. The expressive power of NL-WFA and the proposed learning algorithm are assessed on both synthetic and real world data, showing that NL-WFA can lead to smaller model sizes and infer complex grammatical structures from data.

2018-01-01

AISTATS (publié)

proceedings.mlr.press

Optimizing Home Energy Management and Electric Vehicle Charging with Reinforcement Learning

Di Wu

Vincent Francois-Lavet

Doina Precup

Benoit Boulet

Smart grids are advancing the management efficiency and security of power grids with the integration of energy storage, distributed controll… (voir plus)ers, and advanced meters. In particular, with the increasing prevalence of residential automation devices and distributed renewable energy generation, residential energy management is now drawing more attention. Meanwhile, the increasing adoption of electric vehicle (EV) brings more challenges and opportunities for smart residential energy management. This paper formalizes energy management for the residential home with EV charging as a Markov Decision Process and proposes reinforcement learning (RL) based control algorithms to address it. The objective of the proposed algorithms is to minimize the long-term operating cost. We further use a recurrent neural network (RNN) to model the electricity demand as a preprocessing step. Both the RNN prediction and latent representations are used as additional state features for the RL based control algorithms. Experiments on real-world data show that the proposed algorithms can significantly reduce the operating cost and peak power consumption compared to baseline control algorithms.

2018-01-01

(publié)

www.semanticscholar.org

Tensor Regression Networks with various Low-Rank Tensor Approximations

Xingwei Cao

Joelle Pineau

Tensor regression networks achieve high compression rate of neural networks while having slight impact on performances. They do so by imposi… (voir plus)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.

2017-12-27

ArXiv (prépublication)

arxiv.org

Neural Network Based Nonlinear Weighted Finite Automata

Tianyu Li

Doina Precup

Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models. Given the recent succ… (voir plus)esses of nonlinear models in machine learning, it is natural to wonder whether ex-tending WFA to the nonlinear setting would be beneficial. In this paper, we propose a novel model of neural network based nonlinearWFA model (NL-WFA) along with a learning algorithm. Our learning algorithm is inspired by the spectral learning algorithm for WFAand relies on a nonlinear decomposition of the so-called Hankel matrix, by means of an auto-encoder network. The expressive power of NL-WFA and the proposed learning algorithm are assessed on both synthetic and real-world data, showing that NL-WFA can lead to smaller model sizes and infer complex grammatical structures from data.

2017-09-13

ArXiv (prépublication)

arxiv.org

Hierarchical Methods of Moments

Matteo Ruffini

Borja Balle

Spectral methods of moments provide a powerful tool for learning the parameters of latent variable models. Despite their theoretical appeal,… (voir plus) the applicability of these methods to real data is still limited due to a lack of robustness to model misspecification. In this paper we present a hierarchical approach to methods of moments to circumvent such limitations. Our method is based on replacing the tensor decomposition step used in previous algorithms with approximate joint diagonalization. Experiments on topic modeling show that our method outperforms previous tensor decomposition methods in terms of speed and model quality.

arxiv.org

Multitask Spectral Learning of Weighted Automata