Search Results for author:
Found 10 papers, 3 papers with code
Predictive Coding for Locally-Linear Control
High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks.
Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems
We propose an efficient inference method for switching nonlinear dynamical systems.
Training Variational Autoencoders with Buffered Stochastic Variational Inference
The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets.
Amortized Inference Regularization
In this paper, we leverage the fact that VAEs rely on amortized inference and propose techniques for amortized inference regularization (AIR) that control the smoothness of the inference model.
A DIRT-T Approach to Unsupervised Domain Adaptation
Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable.
Bottleneck Conditional Density Estimation
We introduce a new framework for training deep generative models for high-dimensional conditional density estimation.
Adobe-MIT submission to the DSTC 4 Spoken Language Understanding pilot task
The Dialog State Tracking Challenge 4 (DSTC 4) proposes several pilot tasks.
Robust Dialog State Tracking for Large Ontologies
The Dialog State Tracking Challenge 4 (DSTC 4) differentiates itself from the previous three editions as follows: the number of slot-value pairs present in the ontology is much larger, no spoken language understanding output is given, and utterances are labeled at the subdialog level.
Efficient Thompson Sampling for Online Matrix-Factorization Recommendation
Matrix factorization (MF) collaborative filtering is an effective and widely used method in recommendation systems.
MCMC for Hierarchical Semi-Markov Conditional Random Fields
In this contribution, we propose a new approximation technique that may have the potential to achieve sub-cubic time complexity in length and linear time depth, at the cost of some loss of quality.
