A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Qualitative analysis of MC dropout for NN model uncertainty.
A fast single-shot MC dropout method for neural networks.
MC-CP combines adaptive MC dropout with conformal prediction for robust uncertainty quantification.
MC Dropout is re-evaluated as not Bayesian, affecting predictive posterior and multimodality.
Enhances uncertainty estimation in medical image segmentation.
Enhances uncertainty estimation in neural networks using Dirichlet-based MC Dropout.
A fast method for neural networks that provides uncertainty measures.
Batch normalisation doesn't affect variational inference but fails for larger batch sizes.
Study on MC dropout in wide neural networks and its convergence to Gaussian processes.
Bayesian Neural Networks improve uncertainty modeling in facial emotion recognition.
Develops a neural surrogate for proton dose calculation using Monte Carlo dropout uncertainty.
Early detection of incipient faults is of vital importance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is kn…
Develops a multilevel Monte Carlo framework with dropout for efficient uncertainty quantification.
We show that dropout training is best understood as performing MAP estimation concurrently for a family of conditional models whose objectives are themselves lower bounded by the original dropout objective. This discovery allows us to pick any model from this family after training, which leads to a substantial improvem…
Study on Monte-Carlo dropout for uncertainty estimation in neural networks.
Simplifies neural regression by combining two sub-networks for predictions and uncertainties.
A cubing strategy identifies stable hyperparameter regions for uncertainty quantification in spatial deep learning.
To simultaneously address the rising need of expressing uncertainties in deep learning models along with producing model outputs which are consistent with the known scientific knowledge, we propose a novel physics-guided architecture (PGA) of neural networks in the context of lake temperature modeling where the physica…
QUAM improves uncertainty quantification in deep learning models.
We propose Radial Bayesian Neural Networks (BNNs): a variational approximate posterior for BNNs which scales well to large models while maintaining a distribution over weight-space with full support. Other scalable Bayesian deep learning methods, like MC dropout or deep ensembles, have discrete support-they assign zero…
Two main obstacles preventing the widespread adoption of variational Bayesian neural networks are the high parameter overhead that makes them infeasible on large networks, and the difficulty of implementation, which can be thought of as "programming overhead." MC dropout [Gal and Ghahramani, 2016] is popular because it…
We prove, under two sufficient conditions, that idealised models can have no adversarial examples. We discuss which idealised models satisfy our conditions, and show that idealised Bayesian neural networks (BNNs) satisfy these. We continue by studying near-idealised BNNs using HMC inference, demonstrating the theoretic…
The paper introduces a method to decompose variance in twin networks for better treatment effect estimation.
We consider active learning of deep neural networks. Most active learning works in this context have focused on studying effective querying mechanisms and assumed that an appropriate network architecture is a priori known for the problem at hand. We challenge this assumption and propose a novel active strategy whereby …
Deep active inference agents learn complex environments using Monte-Carlo methods.
Deep neural networks (DNNs) provide state-of-the-art results for a multitude of applications, but the approaches using DNNs for multimodal audiovisual applications do not consider predictive uncertainty associated with individual modalities. Bayesian deep learning methods provide principled confidence and quantify pred…
Advances in deep neural network (DNN) based molecular property prediction have recently led to the development of models of remarkable accuracy and generalization ability, with graph convolution neural networks (GCNNs) reporting state-of-the-art performance for this task. However, some challenges remain and one of the …
Paper confirms MCS spaces are equivalent to CS sets.
Bayesian active learning improves stress and affect detection on wearable devices.
Bayesian approach improves image captioning quality metrics.
Measuring uncertainty is a promising technique for detecting adversarial examples, crafted inputs on which the model predicts an incorrect class with high confidence. But many measures of uncertainty exist, including predictive en- tropy and mutual information, each capturing different types of uncertainty. We study th…
Let be a non-compact geometrically finite hyperbolic 3-manifold without cusps of rank 1. The deformation space $\mc{H}$ of can be identified with the Teichmüller space $\mc{T}$ of the conformal boundary of as the graph of a section in $T^*\mc{T}$. We construct a Hermitian holomorphic line bundle $\mc{L}$ on…
New algebraic structures help categorify link invariants.
We determine the homogeneous Kähler diffeomorphism which expresses the Kähler two-form on the Siegel-Jacobi ball $\mc{D}^J_n=\C^n\times \mc{D}_n$ as the sum of the Kähler two-form on $\C^n$ and the one on the Siegel ball $\mc{D}_n$. The classical motion and quantum evolution on $\mc{D}^J_n$ determined by a hermiti…
We give a homological characterization of -manifolds whose universal covering $\Wi M$ has Gromov's macroscopic dimension $\dim_{mc}\Wi M<n$. As the result we distinguish from the macroscopic dimension defined by the author \cite{Dr}. We prove the inequality $\dim_{mc}\Wi M<\dim_{MC}\Wi M=n$ f…
Ensemble approaches for uncertainty estimation have recently been applied to the tasks of misclassification detection, out-of-distribution input detection and adversarial attack detection. Prior Networks have been proposed as an approach to efficiently \emph{emulate} an ensemble of models for classification by paramete…
The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent. Many calibration methods in the literature have been proposed to improve the predictive uncertainty of DNNs which are generally not well-calibrated. H…
Paper proposes a method to improve prediction intervals for neural networks.
We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA), which computes the first moment of stochastic gradient descent (SGD) iterates with a modified learning rate schedule, has recently been sho…
Favour speeds up variance estimation in BNNs, making them practical for performance-critical tasks.
Advanced Dropout improves DNN performance without requiring model-specific dropout techniques.
Paper detects gradual changes in cluster structure using MC fusion.
We study the structure of classical groups of equivalences for smooth multigerms , and extend several known results for monogerm equivalences to the case of mulitgerms. In particular, we study the group $\A$ of source- and target diffeomorphism germs, and its stabilizer $\A_f$. For monogerms $…
ADRL improves participant selection in MCS systems.
Proposes mCS for multivariate selection with FDR control.
Dropout is a simple but efficient regularization technique for achieving better generalization of deep neural networks (DNNs); hence it is widely used in tasks based on DNNs. During training, dropout randomly discards a portion of the neurons to avoid overfitting. This paper presents an enhanced dropout technique, whic…
Compressed Monte Carlo improves efficiency in Bayesian inference.
Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes for intelligent dropout can lead to better generalization as compared to the tra…