Paper improves graph convolutional networks by adjusting filter size.
problem Improving predictive performance of graph convolutional networks.
method Introducing a hyper-parameter to influence filter size in graph convolutions.
result Improves predictive performance of Deep Graph Convolutional Networks.
A Bloom filter approach combined with Transformer models improves accuracy for machine learning tasks on opaque IDs.
problem Improving accuracy for machine learning tasks on opaque IDs with large vocabulary sizes.
method Applying hash functions to map opaque IDs to multiple hash tokens, similar to a Bloom filter, and using a multi-layer Transformer to process these digests.
result Models outperform those without hashing and sampled softmax, achieving high accuracy with a smaller computational budget.
BSF algorithm reduces neural network size and selects features efficiently.
problem Neural network size and feature selection optimization.
method Binary Stochastic Filtering (BSF) layer that penalizes information, stochastically passes or drops features.
result Multifold decrease in neural network size and optimal feature selection.
Kernel adaptive filters (KAF) are a class of powerful nonlinear filters developed in Reproducing Kernel Hilbert Space (RKHS). The Gaussian kernel is usually the default kernel in KAF algorithms, but selecting the proper kernel size (bandwidth) is still an open important issue especially for learning with small sample s…
Large filters improve performance but are costly; this work uses learned box filters and summed-area tables.
problem Improving performance in dense prediction tasks like human pose estimation with large filters.
method Adopted learnable box filters and summed-area tables to reduce computational cost and maintain performance.
result Demonstrated competitive performance on human pose estimation benchmarks.
Enhanced ensemble filters use machine learning to improve accuracy in filtering models.
problem Accuracy limitations of traditional ensemble Kalman filters.
method Introduces a measure neural mapping (MNM) to map joint predicted state and observation to updated state estimates.
result Superior root-mean-square-error performance compared to leading methods in filtering models.
A new model optimizes Bloom filters using machine learning.
problem Improving the efficiency of Bloom filters for data sets.
method Modeling learned Bloom filters with machine learning, optimizing with sandwiching method.
result Optimized learned Bloom filters provide improved performance.
Holistic Filter Pruning reduces DNN complexity efficiently.
problem Redundant parameters in deep neural networks.
method Holistic Filter Pruning (HFP) for efficient DNN training.
result Achieves state-of-the-art performance with 60% reduction in multiplications on ImageNet.
This work prunes CNN filters based on their functionality, not just size.
problem Redundant filters in CNNs waste computation resources.
method Functionality-oriented filter pruning method.
result Pruning based on functionality optimizes computation and interprets filter importance.
A new SOHP filter improves trend estimation in economic time series.
problem Improving trend estimation in nonlinear economic time series.
method Recursive application of one-sided HP filter on updated cyclical components, combined with an incremental HP filtering algorithm.
result Better performance of SOHP filter compared to other HP-type filters on real economic data.
Explicit encoding of group actions in deep features makes it possible for convolutional neural networks (CNNs) to handle global deformations of images, which is critical to success in many vision tasks. This paper proposes to decompose the convolutional filters over joint steerable bases across the space and the group …
Strong inductive biases prevent harmless interpolation in overparameterized models.
problem Understanding the conditions under which overparameterized models can interpolate noise without overfitting.
method Theoretical analysis of high-dimensional kernel regression and deep neural networks, focusing on the role of inductive biases.
result The strength of an estimator's inductive bias determines whether interpolation is harmless or requires fitting noise for good generalization.
Pruning CNNs by removing less important filters based on empirical loss changes.
problem Reducing memory and computation requirements for CNNs on resource-limited devices.
method Developed a novel filter importance norm based on empirical loss changes, and used sampling and ranking to prune filters.
result Reduced 60% of parameters and 64% of FLOPs with less than 0.6% accuracy drop.
CAOL learns filters from large datasets, and this paper analyzes its performance.
problem Understanding how dataset size impacts CAOL filter updates.
method Analyzes the impact of dataset size on CAOL filter updates using deterministic and probabilistic bounds.
result Empirical evidence suggests that using more training data can improve CAOL performance.
A new method approximates deep neural networks using Kalman Filters.
problem Approximating deep neural networks with limited data.
method Matrix Ensemble Kalman Filter-based multi-arm ANN (MEnKF-ANN).
result MEnKF-ANN can adequately approximate LSTM networks and provide uncertainty estimates.
Over the last decade, both the neural network and kernel adaptive filter have successfully been used for nonlinear signal processing. However, they suffer from high computational cost caused by their complex/growing network structures. In this paper, we propose two random Euler filters for complex-valued nonlinear filt…
This paper addresses the problem of filtering with a state-space model. Standard approaches for filtering assume that a probabilistic model for observations (i.e. the observation model) is given explicitly or at least parametrically. We consider a setting where this assumption is not satisfied; we assume that the knowl…
DNNs improve SIMP method but not spatially invariant, study shows.
problem Improving SIMP method with DNNs but maintaining spatial invariance.
method Use of DNNs for density field generation, study of NTK filter properties.
result DNNs lead to a non-spatially invariant filter, requiring embeddings for spatial invariance.
Compression method reduces model size while maintaining accuracy.
problem Deep neural networks are large and resource-intensive.
method Iteratively drops correlated filters, re-optimizes, and finetunes.
result State-of-the-art FLOPs compression rates with excellent predictive performance.
ScDCFNet improves multiscale image classification with reduced model size.
problem Improving performance in multiscale image classification.
method Decomposed convolutional filters for ST-equivariant CNNs.
result ScDCFNet achieves significantly improved performance in multiscale image classification.
Prunes CNNs by removing redundant filters with provable guarantees.
problem Redundant filters in over-parameterized neural networks.
method Sampling-based approach using saliency scores and importance sampling.
result Consistently generates sparser and more efficient models.
We introduce a probabilistic approach to the LMS filter. By means of an efficient approximation, this approach provides an adaptable step-size LMS algorithm together with a measure of uncertainty about the estimation. In addition, the proposed approximation preserves the linear complexity of the standard LMS. Numerical…
A new method for state space partitioning in block particle filtering reduces bias and variance.
problem Overcoming the curse of dimensionality in non-linear, non-Gaussian state space estimation.
method Formulates state space partitioning as a clustering problem and uses spectral clustering with constraints.
result The proposed method effectively groups correlated state variables into smaller blocks, reducing bias and variance.
Compressing convolutional neural networks (CNNs) is essential for transferring the success of CNNs to a wide variety of applications to mobile devices. In contrast to directly recognizing subtle weights or filters as redundant in a given CNN, this paper presents an evolutionary method to automatically eliminate redunda…
A new ML-based filter improves data assimilation for nonlinear systems.
problem Improving data assimilation for nonlinear systems using ensemble methods.
method Developed a machine learning-based conditional mean filter (ML-EnCMF) integrating ANN and linear functions.
result ML-EnCMF outperforms EnKF and likelihood-based EnCMF in nonlinear systems.
New adaptive filters reduce energy consumption in electronic devices.
problem Reducing energy consumption in adaptive filtering algorithms.
method Data-selective adaptive filters, set-membership (SM) filters, trinion and quaternion systems, partial-updating, LMS and recursive LMS algorithms.
result Improved adaptive filtering algorithms with reduced computational complexity and enhanced stability.
New method combines ODE filters and numerical quadrature to propagate model uncertainty.
problem Propagation of model uncertainty in ODE solutions with uncertain parameters.
method Combining ODE filters with numerical quadrature.
result Effective propagation of both numerical and parametric uncertainty.
A new method estimates time-varying parameters in earth system models using offline and online data assimilation.
problem Estimating time-varying parameters in complex earth system models.
method Hybrid Offline Online Parameter Estimation with Particle Filtering (HOOPE-PF)
result HOOPE-PF outperforms existing methods, especially with small ensemble sizes.
Graphon autoencoder generates graphs with arbitrary sizes using Chebyshev filters.
problem Generating graphs with arbitrary sizes and arbitrary structures.
method Induces graphons from observed graphs, uses Chebyshev filters for latent representation, and learns encoder and decoder to minimize Wasserstein distance.
result Graphon autoencoder provides a new paradigm for graph generation with good generalizability and transferability.
Deep learning predicts fit for fashion e-commerce.
problem Predicting correct fit for customer satisfaction and cost reduction.
method Deep learning content-collaborative approach using customer and article embeddings.
result Significant improvement over state-of-the-art methods.
Filtered conformal ellipsoids for graph-native time series
problem Joint prediction sets for multivariate time series
method Filtered conformal ellipsoids
result Sharper at-target ellipsoids than static-covariance and non-filter baselines
Improved SVI with adjustable annealing for better optimization.
problem Improving optimization in stochastic variational inference.
method Tuneable stochastic annealing in SVI with adjustable batch size.
result Approximation to maximum entropy stochastic gradient at desired variance level.
Online learners track optimal solutions with constant step-size.
problem Tracking optimal solutions in online learning settings.
method Established a link between steady-state performance and tracking performance using analogies with adaptive filters.
result Inferred tracking performance from steady-state expressions directly.
Locality helps in learning from high-dimensional data.
problem Understanding how convolutional neural networks learn from high-dimensional data.
method Teacher-student framework for kernel regression with convolutional kernels.
result Locality is key to determining the learning curve exponent in high-dimensional data.
New method improves Kalman filtering and smoothing for large state spaces.
problem High computational cost and uncertainty in large-scale Kalman filtering.
method Probabilistic numerical method leveraging GPU acceleration and tunable trade-off.
result Mitigates scaling issues and provides more accurate uncertainty estimates.
Kronecker trend filtering improves lattice data smoothing.
problem Estimating smooth functions on lattice data.
method Penalized least squares with Kronecker products of univariate trend filtering penalties.
result Kronecker trend filtering outperforms linear smoothers in high dimensions.
A new method reduces high-dimensional filtering to quadratic complexity.
problem High-dimensional dynamical systems inference and simulation.
method Low-rank Kalman filtering using dynamical low-rank integrator.
result The method reproduces exact Kalman filter in low-rank limit.
The paper tackles reward-relevance in offline RL with sparse decision dynamics.
problem Offline reinforcement learning with sparse decision dynamics and estimation sparsity.
method Reward-filtered least-squares policy evaluation using thresholded lasso.
result The method provides theoretical guarantees with sample complexity dependent on sparse component size.
Ternary MobileNets improve efficiency and accuracy on constrained devices.
problem Efficiently compressing MobileNets for real-time applications on constrained devices.
method Per-layer hybrid filter banks for ternary quantization of MobileNets.
result 27.98% energy savings and 51.07% reduction in model size with comparable accuracy.
Proposes continuous convolution layers for flexible feature map resizing.
problem Fixed stride limitations in discrete convolution layers.
method Introduces Continuous Convolution (CC) layers that use learned continuous functions.
result Dynamic and consistent resizing of feature maps at any scale, non-integer and axis-dependent.
The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the reliance on huge amounts of labeled data and specialized hardware can be a limiti…
Classical collaborative filtering, and content-based filtering methods try to learn a static recommendation model given training data. These approaches are far from ideal in highly dynamic recommendation domains such as news recommendation and computational advertisement, where the set of items and users is very fluid.…
FRN layer eliminates batch dependence in deep learning, improving performance across various tasks.
problem Batch Normalization's dependency on mini-batch elements can degrade performance for small batches.
method Filter Response Normalization (FRN) operates independently on each activation channel of each batch element.
result FRN layer outperforms BN and other alternatives in various settings for all batch sizes.
Improved action detection for multi-person videos using attention filtering.
problem Difficulty in distinguishing relevant parts of multi-person videos for action detection.
method Fovea attention filtering and generalized binary loss function.
result 20% relative improvement in mAP over baseline in AVA dataset.
In this work, we study stability of distributed filtering of Markov chains with finite state space, partially observed in conditionally Gaussian noise. We consider a nonlinear filtering scheme over a Distributed Network of Agents (DNA), which relies on the distributed evaluation of the likelihood part of the centralize…
Efficiently learns neural network parameters from streaming data.
problem Online learning of neural networks from non-stationary data streams.
method Low-rank extended Kalman filtering for approximate Bayesian inference.
result Significantly faster learning and adaptation to changing distributions.
Analog methods improve forecast accuracy in complex models.
problem Improving forecast accuracy in complex models like Lorenz-96.
method Constructing analogs using variational autoencoders for ensemble data assimilation.
result Constructed analogs perform as well as a full ensemble square root filter.
Generalized cross validation (GCV) is one of the most important approaches used to estimate parameters in the context of inverse problems and regularization techniques. A notable example is the determination of the smoothness parameter in splines. When the data are generated by a state space model, like in the spline c…