Representation mixing combines character and phoneme inputs for flexible TTS synthesis.
problem Limited control over pronunciation in character or phoneme-based TTS systems.
method Representation mixing combines multiple linguistic inputs in a single encoder.
result Flexibility in choosing between character, phoneme, or mixed representations during inference.
Model captures system input variations in latent space for actionable dynamics.
problem Learning dynamical systems from data without prescribing a mathematical model.
method Structured latent ODE model with stochastic factors of variation for each input.
result Improves generation of time-series data and inference of system inputs over baselines.
Flexible embedding framework for diverse data types.
problem Limited applicability of existing embedding learning methods.
method A flexible framework using entity-relation-matrices and sampling mechanism.
result Framework outperforms state-of-the-art approaches in various tasks.
We consider the problem of impulse response estimation of stable linear single-input single-output systems. It is a well-studied problem where flexible non-parametric models recently offered a leap in performance compared to the classical finite-dimensional model structures. Inspired by this development and the success…
A new method for Gaussian Processes handles mixed continuous and categorical inputs.
problem Modeling cross-correlations between continuous and categorical data.
method Low-Rank Correlation (LRC) method for Gaussian Processes with flexible rank approximation.
result LRC outperforms existing methods in estimating cross-correlations and predicting response surfaces.
Neural network based generative models with discriminative components are a powerful approach for semi-supervised learning. However, these techniques a) cannot account for model uncertainty in the estimation of the model's discriminative component and b) lack flexibility to capture complex stochastic patterns in the la…
Bias and flexibility trade off in learning algorithms.
problem Understanding the trade-off between bias and expressivity in learning algorithms.
method Measuring expressivity using entropy on algorithm outcome distributions, and deriving bounds on bias and expressivity.
result There is a necessary trade-off between bias and expressivity in learning algorithms.
Proposes flexible dilation networks for better time series analysis.
problem Fixed dilation limits flexibility in time series analysis.
method End-to-end learnable dilation layers and independent kernels.
result Improves efficiency and flexibility in training.
New framework identifies hidden risks and optionality in American options.
problem Underestimation of flexibility and convexity in early-exercise features.
method Introducing stochasticity into underlying determinants to quantify hidden risks and optionality.
result Remedies conventional pricing systems that underestimate optionality.
Flexible GP model improves wind power prediction accuracy.
problem Accurate probabilistic prediction of wind power for grid stability.
method Heteroscedastic non-stationary Gaussian process with generalised spectral mixture kernel.
result The proposed model outperforms conventional GP models in wind power prediction.
Flexible inference model for multilayer networks with heterogeneous data.
problem Complexity of heterogeneous data in networked datasets.
method Probabilistic generative model using Bayesian framework and Laplace matching.
result Effective detection of overlapping community structures and prediction tasks.
GNet uses Gaussian processes for scalable, flexible neural networks.
problem Large-scale predictive modeling with high computational and storage costs.
method GNet employs Gaussian processes with nonparametric activation functions and a fast algorithm for training and predictions.
result GNet achieves competitive performance across various test problems, including nonlinear function prediction and real-world data regression.
GNet uses Gaussian processes for scalable, flexible neural networks.
problem Large-scale predictive modeling with high computational and storage costs.
method GNet employs Gaussian processes with nonparametric activation functions and a fast algorithm for efficient training and predictions.
result GNet achieves competitive performance across various test problems, including nonlinear function prediction and real-world data regression.
Combines MCTM and NF for flexible multivariate density regression with interpretable marginals.
problem Difficult interpretation of flexible NF models and limitations of MCTM in flexibility.
method Hybrid approach combining MCTM for interpretable marginals and NF for complex joint distributions.
result Demonstrates versatility and improved performance compared to MCTM and other NF models.
Flexible model for complex relationships using Bayesian nonparametrics.
problem Complex relationships between variables not well captured by simple models.
method Hierarchical generation of nonlinear features, Bayesian inference, variable selection.
result Find interpretable models with a small set of important features.
PSI models and infers feature attributions efficiently and accurately.
problem Modeling and inferring feature attributions in flexible predictive models.
method Probabilistic Shapley inference (PSI) framework using latent random variables and a masking-based neural network architecture.
result PSI learns feature attribution distributions centered at Shapley values, revealing meaningful uncertainty.
Simplified DGPs training by fixing inducing inputs to subset of data.
problem Challenging training of deep Gaussian processes.
method Fixed subset of data for inducing inputs, variational sampling.
result Significant reduction in trainable parameters and computation cost without performance degradation.
Develops a new flexible grid trading model using ANN and SSO.
problem Improving automated trading strategies in financial markets.
method Combines SSO algorithm with ANN for optimizing trading parameters.
result Provides a robust and efficient trading model with better returns.
Kernel methods have great promise for learning rich statistical representations of large modern datasets. However, compared to neural networks, kernel methods have been perceived as lacking in scalability and flexibility. We introduce a family of fast, flexible, lightly parametrized and general purpose kernel learning …
Approach generates multiple correct predictions from single supervision.
problem Single correct prediction from multiple possible alternatives.
method Develops an approach to generate multiple high-quality predictions.
result Can generate high-quality outputs different from observed.
The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves in-depth study because it characterizes a fixed network capacity which can…
Sparse Gaussian Processes improve scalability by learning inducing points from data.
problem Scaling issues in Gaussian Processes due to cubic computational cost.
method Amortized learning of inducing points and variational posterior parameters using neural networks.
result Significant reduction in the number of inducing points, improving scalability.
We propose a new input perturbation mechanism for publishing a covariance matrix to achieve (ε,0)-differential privacy. Our mechanism uses a Wishart distribution to generate matrix noise. In particular, We apply this mechanism to principal component analysis. Our mechanism is able to keep the positive semi-definitene…
The ACCRU framework improves probabilistic forecasts by capturing input-dependent uncertainty.
problem Uncertainty in deterministic predictions, especially for skewed and non-Gaussian errors.
method Neural network trained with a loss function balancing accuracy and reliability to learn input-dependent, non-Gaussian uncertainty distributions.
result Improves probabilistic forecasts relative to existing methods, capturing skewed and non-Gaussian errors.
Paper proposes a new method for learning kernels that depend on both inputs and outputs.
problem Common kernels are limited in their ability to handle complex tasks.
method Developed a spectral kernel learning framework that uses non-stationary kernels and learns from data.
result Derived a data-dependent generalization error bound and suggested regularization terms.
URN neural network dynamically generates various neural structures during training.
problem Creating neural networks with flexible, dynamic structures during training.
method Introduced Unstructured Recursive Network (URN) and used gradient descent on a single loss function.
result Different neural structures can emerge from a single URN during training.
Variational autoencoders often collapse, showing latent variables are non-identifiable.
problem Posterior collapse in variational autoencoders due to non-identifiable latent variables.
method Proves latent variable non-identifiability causes posterior collapse. Proposes latent-identifiable models using Brenier maps and input convex neural networks.
result Latent-identifiable models resolve posterior collapse and provide meaningful representations.
We introduce a new regression framework, Gaussian process regression networks (GPRN), which combines the structural properties of Bayesian neural networks with the non-parametric flexibility of Gaussian processes. This model accommodates input dependent signal and noise correlations between multiple response variables,…
Random projections improve GP regression performance, reducing high-dimensional inputs to 1D.
problem Gaussian processes struggle with high-dimensional inputs, leading to overfitting and high computational cost.
method Use additive sums of kernels operating on random projections of inputs.
result Predictive performance converges to full-dimensional kernel performance with increasing projections, even in 1D.
Proposes regularization for robust image models using Wasserstein geometry.
problem Robustness to in-class variations in input data.
method Wasserstein-2 geometry, Tikhonov-type regularizer, data augmentation.
result Improves generalization under adversarial perturbations and large variations.
A new method combines experts' opinions to train regression models with noisy labels.
problem Training regression models with noisy labels from multiple experts.
method Estimate each labeler's expertise and combine opinions using learned weights.
result Empirically outperforms existing techniques on simulated and real data.
Develops HDNNs for mixed geoscience data inputs.
problem Lack of multisource, multi-scale information in deep learning studies.
method Hybrid architecture combining feature and target learning.
result HDNNs achieve higher accuracy and better generalization in reservoir prediction.
A new model for Gaussian process experts tackles scalability and uncertainty issues.
problem Scalability and excessive number of experts degrade predictive performance and increase uncertainty.
method Nested partitioning scheme infers the number of components, a generalised GP framework accommodates multiple response types, and a factorised exponential family structure handles multiple input types.
result Effectiveness demonstrated on synthetic data and an Alzheimer's challenge dataset.
Framework detects novel inputs in neural networks by monitoring hidden layers.
problem Novel inputs not classified by neural networks during training.
method Abstraction-based monitoring of hidden layers using 'boxes' to identify novel behaviors.
result Framework efficiently detects novel inputs with a balance between false warnings and true positives.
Ensemble quantile classifier improves performance on high-dimensional data.
problem Discriminating high-dimensional data with heavy-tailed or skewed inputs.
method Regularized quantile classifier that assigns variable weights.
result Consistently estimates minimal population loss and is Bayes optimal.
The Gaussian process latent variable model (GP-LVM) provides a flexible approach for non-linear dimensionality reduction that has been widely applied. However, the current approach for training GP-LVMs is based on maximum likelihood, where the latent projection variables are maximized over rather than integrated out. I…
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality of the input to the objective can greatly influence a representation's …
A new hashing method handles large-scale data with flexible similarity measures.
problem Efficient nearest neighbour search in large-scale systems with variable labels.
method End-to-end trainable network transforming data to uniform distribution on product of spheres, then hashing to binary form maximizing entropy.
result Outperforms baseline approaches in limited capacity regime.
Flexible nonstationary Gaussian process with neural network parameters.
problem Limited expressiveness of stationary Gaussian processes.
method Nonstationary kernels with neural network parameters trained jointly.
result Better accuracy and log-score compared to stationary and hierarchical models.
Bayesian models combine experts with a flexible gating mechanism for complex data.
problem Theoretical properties of Bayesian mixture-of-experts models with softmax gating remain unexplored.
method Investigated asymptotic behavior of posterior distribution for density estimation, parameter estimation, and model selection.
result Established posterior contraction rates for density estimation and parameter estimation, providing insights for practical model design.
We introduce scalable deep kernels, which combine the structural properties of deep learning architectures with the non-parametric flexibility of kernel methods. Specifically, we transform the inputs of a spectral mixture base kernel with a deep architecture, using local kernel interpolation, inducing points, and struc…
Sketching accelerates structured prediction methods for large datasets.
problem Scaling surrogate kernel methods for large datasets.
method Sketching approximations applied to input and output feature maps.
result Achieves close-to-optimal rates with reduced sketch size.
TTF improves performance of normalizing flows for heavy-tailed distributions.
problem Improving performance of normalizing flows for heavy-tailed distributions.
method Uses a Gaussian base distribution and a final transformation layer to produce heavy tails.
result Experimental results show TTF outperforms current methods, especially in high-dimensional or heavy-tailed scenarios.
Flexible XVAE model for efficient spatial extremes simulation.
problem Complex tail dependence structures in spatial extremes processes.
method Variational autoencoder (XVAE) for modeling flexible and non-stationary dependence.
result XVAE provides fast inference and outperforms traditional models in high dimensions.
A fast method combines deep mixtures of sparse GPs for flexible modeling.
problem Flexible modeling with changing output densities.
method Designing gating network with DNN for selecting sparse GPs, using CCR algorithm.
result The method outperforms competing methods in accuracy and uncertainty quantification.
Janossy pooling averages permutation-sensitive functions over all sequences to create invariant functions.
problem Creating deep, invariant functions for variable-size inputs.
method Janossy pooling: average permutation-sensitive functions over all reorderings.
result Improved performance over state-of-the-art methods.
This paper presents an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data. This is achieved using a mixture model where the mixing coefficients are modeled by a Dirichlet process, allowing us to integrate over the coefficients when performing inference. Critically, this then allows us t…
Statistical learning improves reactive power control in distribution systems.
problem Challenges in reactive power control due to renewable energy sources and flexible loads.
method A deep neural network parameterizes the input-output relationship between grid states and optimal reactive power control. Unknown weights are learned offline to minimize power loss, and inference is fast with matrix-vector multiplications.
result Computational efficiency and robustness to random input perturbations demonstrated in a 47-bus distribution network.