Research Output 1966 2019

Filter
Paper
2019

Accelerating eulerian fluid simulation with convolutional networks

Tompson, J., Schlachter, K., Sprechmann, P. & Perlin, K., Jan 1 2019.

Research output: Contribution to conferencePaper

Linear systems
simulation
Unsupervised learning
Fluids
Euler equations

Dialogwae: Multimodal response generation with conditional Wasserstein auto-encoder

Gu, X., Cho, K., Ha, J. W. & Kim, S., Jan 1 2019.

Research output: Contribution to conferencePaper

Normal distribution
conversation
Neural networks
neural network
Experiments

Diffusion scattering transforms on graphs

Gama, F., Bruna Estrach, J. & Ribeiro, A., Jan 1 2019.

Research output: Contribution to conferencePaper

Scattering
Computer vision
data analysis
Graph

Energy-based generative adversarial networks

Zhao, J., Mathieu, M. & LeCun, Y., Jan 1 2019.

Research output: Contribution to conferencePaper

Discriminators
energy
Image resolution
Logistics
Classifiers

Entropy-SGD: Biasing gradient descent into wide valleys. International Conference on Learning Representations (ICLR) 2017

Chaudhari, P., Choromanska, A., Soatto, S., LeCun, Y., Baldassi, C., Borgs, C., Chayes, J., Sagun, L. & Zecchina, R., Jan 1 2019.

Research output: Contribution to conferencePaper

entropy
Entropy
energy
neural network
learning

Hierarchical RL using an ensemble of proprioceptive periodic policies

Marino, K., Gupta, A., Szlam, A. & Fergus, R., Jan 1 2019.

Research output: Contribution to conferencePaper

reward
Navigation
Ensemble
Reward
Values

Model-predictive policy learning with uncertainty regularization for driving in dense traffic

Henaff, M., LeCun, Y. & Canziani, A., Jan 1 2019.

Research output: Contribution to conferencePaper

predictive model
uncertainty
traffic
costs
learning

Reproducibility in machine learning for health

McDermott, M. B. A., Wang, S., Marinsek, N., Ranganath, R., Ghassemi, M. & Foschini, L., Jan 1 2019.

Research output: Contribution to conferencePaper

Learning systems
Health
health
learning
Learning algorithms

Revisiting auxiliary latent variables in generative models

Lawson, D., Tucker, G., Dai, B. & Ranganath, R., Jan 1 2019.

Research output: Contribution to conferencePaper

ranking
coding
Sampling
Generative
Contrastive

Supervised community detection with line graph neural networks

Chen, Z., Bruna Estrach, J. & Li, L., Jan 1 2019.

Research output: Contribution to conferencePaper

neural network
Neural networks
community
Supervised learning
learning

The Andoni–Krauthgamer–Razenshteyn characterization of sketchable norms fails for sketchable metrics

Khot, S. & Naor, A., Jan 1 2019, p. 1814-1824. 11 p.

Research output: Contribution to conferencePaper

Sketching
Normed Space
Norm
Metric
Metric space

The role of over-parametrization in generalization of neural networks

Neyshabur, B., Li, Z., Bhojanapalli, S., LeCun, Y. & Srebro, N., Jan 1 2019.

Research output: Contribution to conferencePaper

neural network
Neural networks
Network layers
Neural Networks
experiment

Topology and geometry of half-rectified network optimization

Daniel Freeman, C. & Bruna Estrach, J., Jan 1 2019.

Research output: Contribution to conferencePaper

Topology
mathematics
Geometry
study conditions
energy

Tracking the world state with recurrent entity networks

Henaff, M., Weston, J., Szlam, A., Bordes, A. & LeCun, Y., Jan 1 2019.

Research output: Contribution to conferencePaper

Data storage equipment
Turing machines
Parallel architectures
Entity
language

Understanding trainable sparse coding via matrix factorization

Moreau, T. & Bruna Estrach, J., Jan 1 2019.

Research output: Contribution to conferencePaper

Factorization
coding
Glossaries
dictionary
neural network
2018

Boundary-seeking generative adversarial networks

Hjelm, R. D., Jacob, A. P., Che, T., Trischler, A., Cho, K. & Bengio, Y., Jan 1 2018.

Research output: Contribution to conferencePaper

Discriminators
conditioning
Generative
language
learning

Competing with automata-based expert sequences

Mohri, M. & Yang, S., Jan 1 2018, p. 1732-1740. 9 p.

Research output: Contribution to conferencePaper

Automata
Efficient Algorithms
Weighted Automata
N-gram
Regret

Divide and conquer networks

Nowak, A., Folqué, D. & Bruna Estrach, J., Jan 1 2018.

Research output: Contribution to conferencePaper

Computational complexity
Backpropagation
Dynamic programming
learning
reward

Emergent communication in a multi-modal, multi-step referential game

Evtimova, K., Drozdov, A., Kiela, D. & Cho, K., Jan 1 2018.

Research output: Contribution to conferencePaper

communication
information exchange
Communication
Mammals
Bandwidth

Emergent translation in multi-agent communication

Lee, J., Cho, K., Weston, J. & Kiela, D., Jan 1 2018.

Research output: Contribution to conferencePaper

communication
Communication
Electric grounding
language
foreign language

Few-shot learning with graph neural networks

Garcia, V. & Bruna Estrach, J., Jan 1 2018.

Research output: Contribution to conferencePaper

neural network
Neural networks
learning
Supervised learning
Message passing

Intrinsic motivation and automatic curricula via asymmetric self-play

Sukhbaatar, S., Lin, Z., Kostrikov, I., Synnaeve, G., Szlam, A. & Fergus, R., Jan 1 2018.

Research output: Contribution to conferencePaper

intrinsic motivation
Curricula
curriculum
reward
Curriculum

Proximity variational inference

Altosaar, J., Ranganath, R. & Blei, D. M., Jan 1 2018, p. 1961-1969. 9 p.

Research output: Contribution to conferencePaper

Proximity
Statistics
Bayesian networks
Annealing
Initialization

Stable and effective trainable greedy decoding for sequence to sequence learning

Chen, Y., Cho, K., Bowman, S. & Li, V. O. K., Jan 1 2018.

Research output: Contribution to conferencePaper

Decoding
neural network
learning
Neural networks
experiment

Unsupervised neural machine translation

Artetxe, M., Labaka, G., Agirre, E. & Cho, K., Jan 1 2018.

Research output: Contribution to conferencePaper

Supervised learning
triangulation
Triangulation
Profitability
profit

Variational sequential Monte Carlo

Naesseth, C. A., Linderman, S. W., Ranganath, R. & Blei, D. M., Jan 1 2018, p. 968-977. 10 p.

Research output: Contribution to conferencePaper

Sequential Monte Carlo
Stochastic models
Brain
Networks (circuits)
Probabilistic Inference
2016

Accelerating online convex optimization via adaptive prediction

Mohri, M. & Yang, S., Jan 1 2016, p. 848-856. 9 p.

Research output: Contribution to conferencePaper

Online Optimization
Convex optimization
Randomisation
Convex Optimization
Design of Algorithms

Deep multi-scale video prediction beyond mean square error

Mathieu, M., Couprie, C. & LeCun, Y., Jan 1 2016.

Research output: Contribution to conferencePaper

Mean square error
video
Pixels
training method
Optical flows

Oracle performance for visual captioning

Yao, L., Ballas, N., Cho, K., Smith, J. R. & Bengio, Y., Jan 1 2016, p. 141.1-141.13.

Research output: Contribution to conferencePaper

Scalable Gaussian processes for characterizing multidimensional change surfaces

Herlands, W., Wilson, A., Nickisch, H., Flaxman, S., Neill, D., van Panhuis, W. & Xing, E., Jan 1 2016, p. 1013-1021. 9 p.

Research output: Contribution to conferencePaper

Gaussian Process
kernel
Nonseparable
Change Point
Covariance Structure

Super-resolution with deep convolutional sufficient statistics

Bruna Estrach, J., Sprechmann, P. & LeCun, Y., Jan 1 2016.

Research output: Contribution to conferencePaper

statistics
Statistics
Neural networks
Inverse problems
neural network

The variational Gaussian process

Tran, D., Ranganath, R. & Blei, D. M., Jan 1 2016.

Research output: Contribution to conferencePaper

learning
Unsupervised learning
Inference
Learning Model
Generative

Variational tempering

Mandt, S., McInerney, J., Abrol, F., Ranganath, R. & Blei, D., Jan 1 2016, p. 704-712. 9 p.

Research output: Contribution to conferencePaper

Tempering
Annealing
Schedule
Subsampling
Markov processes
2015

Audio source separation with discriminative scattering networks

Sprechmann, P., Bruna Estrach, J. & LeCun, Y., Jan 1 2015.

Research output: Contribution to conferencePaper

Source separation
Scattering
Network architecture
Factorization
Convolution
learning
Communication
worker
communication
local communication

Embedding word similarity with neural machine translation

Hill, F., Cho, K., Jean, S., Devin, C. & Bengio, Y., Jan 1 2015.

Research output: Contribution to conferencePaper

vocabulary
language
Syntactics
Linguistics
Machine Translation

Explorations on high dimensional landscapes

Sagun, L., Ugur Güney, V., Ben Arous, G. & LeCun, Y., Jan 1 2015.

Research output: Contribution to conferencePaper

Spin glass
student teacher
Students
simulation
experiment

Fast convolutional nets with fbfft: A GPU performance evaluation

Vasilache, N., Johnson, J., Mathieu, M., Chintala, S., Piantino, S. & LeCun, Y., Jan 1 2015.

Research output: Contribution to conferencePaper

Convolution
evaluation
performance
Fast Fourier transforms
CNN

Neural machine translation by jointly learning to align and translate

Bahdanau, D., Cho, K. & Bengio, Y., Jan 1 2015.

Research output: Contribution to conferencePaper

learning
Neural networks
performance
Machine Translation
intuition

The survival filter: Joint survival analysis with a latent time series

Ranganath, R., Perotte, A., Elhadad, N. & Blei, D. M., Jan 1 2015, p. 742-751. 10 p.

Research output: Contribution to conferencePaper

Time series
Health
Statistics

Training convolutional networks with noisy labels

Sukhbaatar, S., Bruna Estrach, J., Paluri, M., Bourdev, L. & Fergus, R., Jan 1 2015.

Research output: Contribution to conferencePaper

Labels
Availability
infrastructure
experiment
Experiments

Unsupervised feature learning from temporal data

Goroshin, R., Bruna Estrach, J., Tompson, J., Eigen, D. & LeCun, Y., Jan 1 2015.

Research output: Contribution to conferencePaper

learning
2014

Bounding the test log-likelihood of generative models

Bengio, Y., Yao, L. & Cho, K., Jan 1 2014.

Research output: Contribution to conferencePaper

model comparison
normalization
Random variables
Probability distributions
Learning algorithms
Convolution
Computer vision
learning
Learning systems
Labels

How to construct deep recurrent neural networks: Proceedings of the Second International Conference on Learning Representations (ICLR 2014)

Pascanu, R., Gulcehre, C., Cho, K. & Bengio, Y., Jan 1 2014.

Research output: Contribution to conferencePaper

Second International
Recurrent neural networks
neural network
learning
Feedforward neural networks

Intriguing properties of neural networks

Szegedy, C., Zaremba, W., Sutskever, I., Bruna Estrach, J., Erhan, D., Goodfellow, I. & Fergus, R., Jan 1 2014.

Research output: Contribution to conferencePaper

neural network
Neural networks
cause
Semantics
artifact

Overfeat: Integrated recognition, localization and detection using convolutional networks. 2nd International Conference on Learning Representations, ICLR 2014

Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R. & LeCun, Y., Jan 1 2014.

Research output: Contribution to conferencePaper

learning
confidence
Localization
Deep learning
Boundary Objects

Spectral networks and deep locally connected networks on graphs

Bruna Estrach, J., Zaremba, W., Szlam, A. & LeCun, Y., Jan 1 2014.

Research output: Contribution to conferencePaper

CNN
Invariance
neural network
Neural networks
experiment
learning
activation
Chemical activation
Layer
2013

Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients

Schaul, T. & LeCun, Y., Jan 1 2013.

Research output: Contribution to conferencePaper

Tuning
learning
estimation procedure
time
Hessian