arXiv research

A new model optimizes Bloom filters using machine learning.

Kernel learning FBSDE filter improves nonlinear filtering efficiency.

Paper learns to rotate filters for group convolutions.

Filtering data with a pre-trained model improves multimodal contrastive learning performance.

Removing or filtering outliers and mislabeled instances prior to training a learning algorithm has been shown to increase classification accuracy. A popular approach for handling outliers and mislabeled instances is to remove any instance that is misclassified by a learning algorithm. However, an examination of which l…

Illustrates interleaved learning with Kalman Filter for linear least squares.

Develops Bayesian filtering for online learning and related problems.

The paper learns an autoregressive filter for unknown dynamical systems with robust guarantees.

RNF learns distinct representations for Bayesian filtering steps, improving time series prediction accuracy and uncertainty.

This paper proves long-time accuracy of ensemble Kalman filters for chaotic and machine-learned systems.

A new ML-based filter improves data assimilation for nonlinear systems.

New deep learning method approximates Benes filter model.

Recursive KalmanNet combines neural networks with Kalman filters for precise state estimation.

Filtered conformal ellipsoids for graph-native time series

NBF combines deep learning with classical filtering for better belief tracking.

SELF filters noisy labels to improve deep learning performance.

Convolutional neural networks (CNNs) have recently emerged as a popular building block for natural language processing (NLP). Despite their success, most existing CNN models employed in NLP share the same learned (and static) set of filters for all input sentences. In this paper, we consider an approach of using a smal…

A deep learning method solves nonlinear filtering problems efficiently.

Proposes a deep latent factor model for better recommendation systems.

Graph filtering framework improves semi-supervised learning efficiency.

QFIL improves offline RL by filtering data to reduce bias and variance.

Paper proves spectral filters can be transferred between graphs.

Differentiable resampling improves particle filter performance.

DEKF maintains stability in LSTM learning with bounded perturbations.

Proposes interpretable filters in CNNs for object classification.

AD-EnKFs use machine learning to improve data assimilation in high-dimensional systems.

Data is said to follow the transform (or analysis) sparsity model if it becomes sparse when acted on by a linear operator called a sparsifying transform. Several algorithms have been designed to learn such a transform directly from data, and data-adaptive sparsifying transforms have demonstrated excellent performance i…

The Kalman filter (KF) is used in a variety of applications for computing the posterior distribution of latent states in a state space model. The model requires a linear relationship between states and observations. Extensions to the Kalman filter have been proposed that incorporate linear approximations to nonlinear m…

We generate transformation-invariant CNNs using context-aware filters.

We cast Amari's natural gradient in statistical learning as a specific case of Kalman filtering. Namely, applying an extended Kalman filter to estimate a fixed unknown parameter of a probabilistic model from a series of observations, is rigorously equivalent to estimating this parameter via an online stochastic natural…

FLUID uses flows to unify filtering and smoothing for complex systems.

Deep density methods improve filtering in high-dimensional systems.

Research shows filtering reduces predictability of cyber-attacks.

Extended Kalman Filter is shown to be a gradient descent in trajectory space.

Enhanced ensemble filters use machine learning to improve accuracy in filtering models.

Advances deep network embedding through multi-filtering GCN.

The paper explores modifications to filter banks for speech recognition.

Improving Bayesian filtering with strictly proper scoring rules

Graph Kalman filters adapt classical filters to graph data.

Improved Kalman filter for non-linear, non-Gaussian data.

Neural Bloom Filters learn set membership in one shot.

This paper presents the construction of a particle filter, which incorporates elements inspired by genetic algorithms, in order to achieve accelerated adaptation of the estimated posterior distribution to changes in model parameters. Specifically, the filter is designed for the situation where the subsequent data in on…

Develops inverse EKF for non-linear systems with stability guarantees and learning unknown dynamics.

New method improves convergence of spatial filters in neural networks.

Robust Kalman filtering method for outlier detection.

A Bloom filter approach combined with Transformer models improves accuracy for machine learning tasks on opaque IDs.

We propose a cloud-based filter trained to block third parties from uploading privacy-sensitive images of others to online social media. The proposed filter uses Distributed One-Class Learning, which decomposes the cloud-based filter into multiple one-class classifiers. Each one-class classifier captures the properties…

Gradient filters track moving parameters under noisy data and misspecification.