Related papers: NAS-X: Neural Adaptive Smoothing via Twisting
Achieving high accuracy on data from domains unseen during training is a fundamental challenge in domain generalization (DG). While state-of-the-art DG classifiers have demonstrated impressive performance across various tasks, they have…
Despite their success, convolutional neural networks are computationally expensive because they must examine all image locations. Stochastic attention-based models have been shown to improve computational efficiency at test time, but they…
Bayesian neural networks (BNNs) require scalable sampling algorithms to approximate posterior distributions over parameters. Existing stochastic gradient Markov Chain Monte Carlo (SGMCMC) methods are highly sensitive to the choice of…
Long Short-Term Memory (LSTM) Recurrent Neural networks (RNNs) rely on gating signals, each driven by a function of a weighted sum of at least 3 components: (i) one of an adaptive weight matrix multiplied by the incoming external input…
Machine learning algorithms, such as Support Vector Machine (SVM) and Deep Neural Network (DNN), have gained a lot of interests recently. When training a machine learning algorithm, randomly shuffle all the training data can improve the…
Latent state space systems are ubiquitous in statistical modelling, arising naturally when a time series is observed through a noisy measurement function, however training deep state space models (DSSM) at scale remains difficult. Two…
Non-autoregressive text to speech (NAR-TTS) models have attracted much attention from both academia and industry due to their fast generation speed. One limitation of NAR-TTS models is that they ignore the correlation in time and frequency…
Mining tasks over sequential data, such as clickstreams and gene sequences, require a careful design of embeddings usable by learning algorithms. Recent research in feature learning has been extended to sequential data, where each instance…
We introduce neural particle smoothing, a sequential Monte Carlo method for sampling annotations of an input string from a given probability model. In contrast to conventional particle filtering algorithms, we train a proposal distribution…
Unsupervised structure learning in high-dimensional time series data has attracted a lot of research interests. For example, segmenting and labelling high dimensional time series can be helpful in behavior understanding and medical…
The focus of this work is on spatial variable selection for scalar-on-image regression. We propose a new class of Bayesian nonparametric models, soft-thresholded Gaussian processes and develop the efficient posterior computation algorithms.…
We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our test-time adaptive models against adversarial examples. ARS extends the analysis of randomized smoothing using $f$-Differential Privacy to certify the adaptive…
Hybrid methods have been shown to outperform pure statistical and pure deep learning methods at both forecasting tasks, and at quantifying the uncertainty associated with those forecasts (prediction intervals). One example is Multivariate…
Use of appropriate initialization to warm-start Reynolds-averaged Navier-Stokes (RANS) simulations of turbulent flow can facilitate convergence and lead to efficient use of computational resources. In this work, a method to model downstream…
Models that employ latent variables to capture structure in observed data lie at the heart of many current unsupervised learning algorithms, but exact maximum-likelihood learning for powerful and flexible latent-variable models is almost…
This study introduces a novel formulation to enhance Support Vector Machines (SVMs) in handling class imbalance and noise. Unlike the conventional Soft Margin SVM, which penalizes the magnitude of constraint violations, the proposed model…
Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior collapse. The former arises as only the last hidden state…
Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge: balancing plasticity (learning new tasks) and stability (preserving past knowledge). Neural…
The support vector machines (SVM) is one of the most widely used and practical optimization based classification models in machine learning because of its interpretability and flexibility to produce high quality results. However, the big…
Automating sleep staging is vital to scale up sleep assessment and diagnosis to serve millions experiencing sleep deprivation and disorders and enable longitudinal sleep monitoring in home environments. Learning from raw polysomnography…