Search Results for author:
Found 20 papers, 8 papers with code
Learning to Lemmatize in the Word Representation Space
We propose an alternative for this, in form of a tool that performs lemmatization in the space of word embeddings.
Riemannian Laplace Approximation with the Fisher Metric
Laplace's method approximates a target density with a Gaussian distribution at its mode.
Warped geometric information on the optimisation of Euclidean functions
We use Riemannian geometry notions to redefine the optimisation problem of a function on the Euclidean space to a Riemannian manifold with a warped metric, and then find the function's optimum along this manifold.
Scalable Stochastic Gradient Riemannian Langevin Dynamics in Non-Diagonal Metrics
Stochastic-gradient sampling methods are often used to perform Bayesian inference on neural networks.
Estimating the Contamination Factor's Distribution in Unsupervised Anomaly Detection
We leverage on outputs of several anomaly detectors as a representation that already captures the basic notion of anomalousness and estimate the contamination using a specific mixture formulation.
Neural network for determining an asteroid mineral composition from reflectance spectra
We aim to develop a fast and robust neural-network-based method for deriving the mineral modal and chemical compositions of silicate materials from their visible and near-infrared spectra.
Lagrangian Manifold Monte Carlo on Monge Patches
The efficiency of Markov Chain Monte Carlo (MCMC) depends on how the underlying geometry of the problem is taken into account.
Traversing Time with Multi-Resolution Gaussian Process State-Space Models
These models have a natural interpretation as discretized stochastic differential equations, but inference for long sequences with fast and slow transitions is difficult.
Reliable Categorical Variational Inference with Mixture of Discrete Normalizing Flows
Variational approximations are increasingly based on gradient-based optimization of expectations estimated by sampling.
Multi-scale Cloud Detection in Remote Sensing Images using a Dual Convolutional Neural Network
Semantic segmentation by convolutional neural networks (CNN) has advanced the state of the art in pixel-level classification of remote sensing images.
Low-Rank Approximations of Second-Order Document Representations
Document embeddings, created with methods ranging from simple heuristics to statistical and deep models, are widely applicable.
Prior Specification for Bayesian Matrix Factorization via Prior Predictive Matching
The behavior of many Bayesian models used in machine learning critically depends on the choice of prior distributions, controlled by some hyperparameters that are typically selected by Bayesian optimization or cross-validation.
Correcting Predictions for Approximate Bayesian Inference
Bayesian models quantify uncertainty and facilitate optimal decision-making in downstream applications.
Variational Bayesian Decision-making for Continuous Utilities
Bayesian decision theory outlines a rigorous framework for making optimal decisions based on maximizing expected utility over a model posterior.
Benchmarks and models for entity-oriented polarity detection
We address the problem of determining entity-oriented polarity in business news.
HCS at SemEval-2017 Task 5: Polarity detection in business news using convolutional neural networks
Task 5 of SemEval-2017 involves fine-grained sentiment analysis on financial microblogs and news.
Importance Sampled Stochastic Optimization for Variational Inference
Variational inference approximates the posterior distribution of a probabilistic model with a parameterized density by maximizing a lower bound for the model evidence.
Group Factor Analysis
Factor analysis provides linear factors that describe relationships between individual variables of a data set.
PinView: Implicit Feedback in Content-Based Image Retrieval
It then retrieves images with a specialized online learning algorithm that balances the tradeoff between exploring new images and exploiting the already inferred interests of the user.
Group-sparse Embeddings in Collective Matrix Factorization
CMF is a technique for simultaneously learning low-rank representations based on a collection of matrices with shared entities.
