Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning fil…
On-device research index
arXiv research
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “Filter Importance”
This work ranks CNN filters based on their importance.
problem Unclear role of CNN neurons in producing output.
method Two methods: Shapley value game theory and Importance switch variational inference.
result Filters with higher importance are more crucial for output.
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.
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.
The ability to track a moving vehicle is of crucial importance in numerous applications. The task has often been approached by the importance sampling technique of particle filters due to its ability to model non-linear and non-Gaussian dynamics, of which a vehicle travelling on a road network is a good example. Partic…
The study reveals flaws in pruning criteria and proposes a new assumption for better filter selection.
problem Flaws in existing pruning criteria for CNNs.
method Empirical experiments and Convolutional Weight Distribution Assumption.
result The Convolutional Weight Distribution Assumption improves filter selection in pruning.
AOFP prunes CNN filters faster and more accurately.
problem Finding optimal CNN width and pruning filters efficiently.
method Binary search, random masking, multi-path framework.
result AOFP achieves faster pruning with minimal accuracy loss.
An Automatic Relevance Determination Prior Bayesian Neural Network for Controlled Variable Selectionstat.ML
Bayesian neural network improves feature selection and prediction.
problem Improving feature selection and prediction accuracy in neural networks.
method BNN-ARD with l2-norm feature importance measure.
result Improves variable selection and predictive performance on real-world data.
Sequential Monte Carlo techniques are useful for state estimation in non-linear, non-Gaussian dynamic models. These methods allow us to approximate the joint posterior distribution using sequential importance sampling. In this framework, the dimension of the target distribution grows with each time step, thus it is nec…
Advances deep network embedding through multi-filtering GCN.
problem Existing attribute embedding methods fail to capture different aspects of node features.
method Multi-filtering Graph Convolution Neural Network (GCN) framework.
result Significant improvement in link prediction and node classification tasks with limited training data.
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.
Proposes IFCDA framework to improve cross-domain adaptation.
problem Negative transfer and difficulty in handling category-irrelevant losses in DA.
method Importance filtered mechanism to generate filtered soft labels, combined with graph-based label propagation.
result Significantly improves performance in both Closed-Set and Open-Set DA scenarios.
New method filters large networks from financial data to reveal key subnetworks.
problem Filtering large dimensional networks to isolate key constituents.
method Exploits spectral properties of high-dimensional data networks, tuning for sparsity and consistency.
result Shows method can interpolate between zero and maximal filtering, preserving spectral properties.
Paper proves spectral filters can be transferred between graphs.
problem Proving spectral filters can be transferred between graphs.
method Introducing the Cayley smoothness space and proving filters in this space are linearly stable.
result Graph spectral filters are transferable if they are in the Cayley smoothness space.
Shrinkage and spectral filtering of correlation matrices: a comparison via the Kullback-Leibler distancephysics.data-an
The problem of filtering information from large correlation matrices is of great importance in many applications. We have recently proposed the use of the Kullback-Leibler distance to measure the performance of filtering algorithms in recovering the underlying correlation matrix when the variables are described by a mu…
Novel filtering method for high-dimensional chaotic systems.
problem Filtering in high-dimensional non-Gaussian models with chaotic dynamics and sparse observations.
method Transportation of measures, convex optimization, probabilistic graphical models, nonlinear couplings.
result State-of-the-art tracking performance on chaotic systems like Lorenz-96 model.
New MCFOs improve learning generative models and time series inference.
problem Challenges in learning generative models and inferring latent trajectories for time series.
method Proposed Monte Carlo filtering objectives (MCFOs) for joint learning and adaptive proposals.
result MCFOs lead to efficient and stable model learning and explain data well.
Improved stock volume prediction using Kalman Filters with various hidden states.
problem Improving accuracy of intraday trading volume prediction.
method Extended Kalman Filter with various hidden states for different stocks, using cross-validation to determine optimal state number.
result Demonstrated improved accuracy through comparison experiments and numerical analysis.
A new spectrum attention mechanism improves time series classification.
problem Improving robustness and classification accuracy in time series classification.
method Proposes a spectrum attention mechanism (SAM) to filter and highlight important frequency components, using L1 regularization and a tumbling window for segmentation.
result Experimental results show that the proposed SSAM method produces better feature representations and improves classification accuracy.
This paper presents a fast Bayesian filtering technique for state estimation.
problem Bottleneck in Bayesian inference for state estimation from noisy sensor data.
method Processor-native uncertainty tracking for uncertainty propagation and inference.
result Deterministic approximate filtering with up to 805x speedup and competitive accuracy.
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.
BeMF improves recommendation reliability in recommender systems.
problem Improving reliability in recommender systems beyond accuracy.
method Bernoulli Matrix Factorization (BeMF) for model-based collaborative filtering.
result BeMF selects more reliable predictions, improving recommendation quality.
On Data-Selective Learningeess.SP
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.
The accuracy of least squares calibration using option premiums and particle filtering of price data to find model parameters is determined. Derivative models using exponential Lévy processes are calibrated using regularized weighted least squares with respect to the minimal entropy martingale measure. Sequential impor…
Develops NFCF to reduce gender bias in social media recommendation systems.
problem Reduces gender bias in collaborative filtering systems on social media data.
method Pre-training and fine-tuning neural collaborative filtering with bias correction techniques.
result Achieves better performance and fairness in gender de-biased recommendations.
Neuron Shapley identifies key neurons in deep networks, improving model accuracy and fairness.
problem Identifying responsible neurons in deep networks for better model performance and fairness.
method Neuron Shapley framework quantifies neuron contributions, accounting for interactions.
result Removing just 30 critical filters can destroy model accuracy, revealing network function.
On-line estimation plays an important role in process control and monitoring. Obtaining a theoretical solution to the simultaneous state-parameter estimation problem for non-linear stochastic systems involves solving complex multi-dimensional integrals that are not amenable to analytical solution. While basic sequentia…
ATPF combines PF and EnKF for better inference in complex systems.
problem Weight degeneracy in PF and approximation errors in EnKF.
method Adversarial learning to improve posterior matching and incorporate kernel methods for optimization.
result ATPF provides theoretical guarantees and practical advantages over PF and EnKF.
SeER hybrid model improves song recommendations and explains them.
problem Improving song recommendations and explaining them.
method Collaborative filtering and deep learning sequence models on MIDI content.
result Personalized explanations capture user preferences.
This paper introduces the kernel mixture network, a new method for nonparametric estimation of conditional probability densities using neural networks. We model arbitrarily complex conditional densities as linear combinations of a family of kernel functions centered at a subset of training points. The weights are deter…
Max-plus operators improve neural network filter selection and pruning.
problem Improving neural network efficiency and reducing redundancy.
method Exploiting Max-plus operators in neural network layers for filter selection and model pruning.
result Max-plus layers enhance filter selection and reduce redundancy without performance loss.
A new filter design improves system identification accuracy.
problem Improving system identification accuracy for various system types.
method Generalized proportionate-type normalized subband adaptive filter (GPtNSAF) using least squares on subband errors with a sparsity penalty.
result GPtNSAF benefits from increasing subbands more than sparsity for quasi-sparse or dispersive systems, and both aspects are complementary for sparse systems.
We propose a principled algorithm for robust Bayesian filtering and smoothing in nonlinear stochastic dynamic systems when both the transition function and the measurement function are described by non-parametric Gaussian process (GP) models. GPs are gaining increasing importance in signal processing, machine learning,…
Paper solves open problem of first-order algorithms for filtering-clustering models.
problem Understanding convergence property of first-order algorithms for filtering-clustering models.
method Identifies a global error bound condition and designs a generalized dual gradient ascent algorithm.
result Proposes optimal first-order algorithms in deterministic, finite-sum, and online settings.
In today's day and age when almost every industry has an online presence with users interacting in online marketplaces, personalized recommendations have become quite important. Traditionally, the problem of collaborative filtering has been tackled using Matrix Factorization which is linear in nature. We extend the wor…
Improved product recommendations using deep learning.
problem Sparse customer purchasing data for personalized recommendations.
method Deep Collaborative Filtering (NCF) with latent variables and Bayesian Optimization.
result NCF achieved highest NDCG performance on proprietary dataset.
A new Fourier model improves ODE prediction.
problem Improving the accuracy of ODE solutions, especially for periodic functions.
method Constructing a Fourier state space model and a hybrid model combining Taylor and Fourier methods.
result The hybrid model can predict ODE solutions more accurately, especially for periodic functions.
Enhances DNNs by selectively learning key image edges.
problem Improving DNN robustness against adversarial attacks.
method Introduces Secure Selective Convolution (SSC) to learn important image edges.
result Significant reduction in attack success rate and imperceptibility of adversarial images.
A method for optimal Bayesian filtering using progressive particle flow and optimal transport maps.
problem Optimizing Bayesian filtering with deterministic particles to avoid degeneration.
method Progressive flow of particles through a sequence of sub-steps, each using an optimal transport map to replace non-equally weighted particles with equally weighted ones.
result The method avoids particle degeneration and simplifies the filtering process by not requiring inversions or monotonicity constraints.
Advances in collaborative filtering and ranking methods.
problem Improving recommendation systems efficiency and accuracy.
method Graph information encoding, pairwise and listwise approaches, regularization techniques, personalization.
result New methods significantly improve recommendation system performance.
Graph neural networks are found to be primarily low-pass filters, not manifold learners.
problem Improving performance and scalability of graph neural networks for graph-structured data.
method Developed a theoretical framework based on graph signal processing.
result Graph neural networks only perform low-pass filtering on feature vectors and do not have non-linear manifold learning property.
New training algorithm enhances SNNs for temporal signal processing.
problem Lack of robust training algorithms for large-scale SNNs.
method Formulated SNN as IIR filters, proposed training algorithm for optimal synapse filter kernels and weights.
result Model and training algorithm outperform state-of-the-art approaches in accuracy.
New research connects evolutionary dynamics to Bayesian learning.
problem Connecting evolutionary biology and Bayesian learning.
method Rigorous mathematical proof using Kushner-Stratonovich equation and gradient flows.
result Discrete time filtering equations converge to Stratonovich interpretation of Kushner-Stratonovich equation.
Feature selection is frequently used as a pre-processing step to machine learning. It is a process of choosing a subset of original features so that the feature space is optimally reduced according to a certain evaluation criterion. The central objective of this paper is to reduce the dimension of the data by finding a…
A method estimates and prunes neural network filters to reduce computation and improve accuracy.
problem Reduction of neural network parameters to save computation and energy.
method Estimates each neuron's contribution to loss using first and second-order Taylor expansions; iteratively removes less important neurons.
result High (>93%) correlation between estimated and true importance; 40% FLOPS reduction with 0.02% top-1 accuracy loss.
Simpler GNNs perform well on graph classification tasks.
problem Understanding what Graph Neural Networks (GNNs) learn and their complexity.
method Dissected GNNs into graph filtering and set function, linearizing them separately.
result Linear graph filtering with non-linear set function is efficient and powerful.
Paper formulates EnKF as optimal transport problem for unique control law.
problem Unique control law for EnKF algorithms.
method Formulated as optimal transportation problem, derived explicit control law.
result Mean squared error converges to zero with finite particles.
Efficient algorithm predicts unknown linear systems with long-term memory.
problem Predicting unknown and partially observed linear dynamical systems with long-term memory.
method Bounding the generalized Kolmogorov width of the Kalman filter model using spectral methods and conducting tight convex relaxation.
result Competes with Kalman filter in hindsight with only logarithmic regret.