Efficient policy learning from observational data using weighted classification reductions.
problem Efficient policy evaluation does not necessarily lead to efficient estimation of policy parameters.
method Proposed an estimation approach based on generalized method of moments, efficient for policy parameters.
result Demonstrated empirical efficiency and regret benefits of a proposed method.
Efficient GP classification using Polya-Gamma data augmentation.
problem Scalable Gaussian Process Classification.
method Stochastic variational approach with closed-form updates.
result Up to two orders of magnitude faster than state-of-the-art.
FiT combines transfer and meta-learning for efficient few-shot image classification.
problem Few-shot image classification in personalized and federated learning settings.
method Combines transfer learning and meta-learning with fixed pretrained backbones and fine-tuned FiLM adapter layers.
result Achieves state-of-the-art accuracy on VTAB-1k benchmark with fewer than 1% of updateable parameters.
RCCNet simplifies CNN for efficient colon cancer nuclei classification.
problem Efficient and precise classification of histological cell nuclei for medical analysis.
method Proposes RCCNet, a simplified CNN architecture with 1.5M parameters.
result Achieved 80.61% accuracy and 0.7887 F1 score on CRCHistoPhenotypes dataset.
New NHCAs improve multi-category classification efficiency.
problem Efficient multi-category classification for real-world problems.
method Twin SVM (TWSVM), Generalized eigenvalue proximal SVM (GEPSVM), Regularized GEPSVM (RegGEPSVM), and Improved GEPSVM (IGEPSVM) with OAA, BT, and TDS approaches.
result TDS-TWSVM outperforms other methods in classification accuracy.
A new method combines classification with population Monte Carlo for efficient ABC.
problem Inefficient particle proposals and subjectivity in ABC methods.
method Classification-PMC, blending adaptive proposals and classification.
result Classification-PMC outperforms state-of-the-art ABC methods in simulations.
QubitHD improves HD computing ML efficiency without sacrificing accuracy.
problem Trade-off between energy efficiency and classification accuracy in HD computing-based ML.
method Stochastically binarizes HD-based algorithms while maintaining comparable classification accuracies.
result 65% improvement in energy efficiency and 95% improvement in training time on FPGA.
PiNet improves graph classification efficiency and accuracy.
problem Graph level classification challenges.
method Attention-based pooling mechanism for graph convolution operations.
result Superior performance and high sample efficiency.
A model verifies during classification to reduce memorization, matching baseline accuracy with fewer parameters.
problem Classification systems require memorizing all classes, leading to increased memory usage and poor sample efficiency.
method Iterative nondifferentiable queries for verification during classification, balancing recognition and verification.
result The model can match baseline accuracy while using fewer parameters, but requires careful balance between recognition and verification.
Efficient graph-based decoding improves extreme classification accuracy.
problem Learning algorithms for extreme classification with large label sets.
method ECOC with loss-based decoding on graph-induced output codes.
result Efficient loss-based decoding on graph output codes improves classification accuracy.
Framework for efficient defect classification and inspection.
problem Adaptive defect classification and inspection from high volume data.
method Continual learning framework for dynamic classifier updates.
result Efficient storage and computational needs reduction.
Efficient deep learning for hyperspectral image classification using active learning.
problem Lack of good-quality labeled samples for deep learning in hyperspectral images.
method Weighted incremental dictionary learning for active selection of training samples.
result The proposed algorithm improves deep learning efficiency and effectiveness in hyperspectral image classification.
Resource-efficient oblique trees reduce neural signal classification costs.
problem Implementing efficient neural signal classifiers on resource-constrained devices.
method Integrating model compression, probabilistic routing, and cost-aware learning.
result Significant reduction in model size and feature extraction cost compared to state-of-the-art models.
AclNet improves audio classification with high accuracy and reduced complexity.
problem Efficiently classifying audio data with high accuracy.
method Proposed AclNet architecture with data augmentation and regularization.
result Achieved state-of-the-art performance on ESC-50 corpus with 85.65% accuracy.
New algorithms reduce communication costs in collaborative learning.
problem Reducing communication costs in collaborative learning.
method Distributed boosting and adaptation to classification noise.
result Communication-efficient algorithms for collaborative PAC learning robust to noise.
META 2 ^\mathbf{2} 2 improves taxonomic classification and abundance estimation in metagenomics with deep learning and memory efficiency.
problem Memory constraints and inefficiencies in taxonomic classification and abundance estimation for metagenomics.
method Developed a novel memory-efficient read classification technique combining deep learning and locality-sensitive hashing, and formulated abundance estimation as a Multiple Instance Learning problem.
result Our approach outperforms conventional methods in both single-read taxonomic classification and abundance estimation, especially when memory is limited.
Efficient algorithms for online multiclass linear classification with bandit feedback under linear separability conditions.
problem Efficient online multiclass linear classification with bandit feedback for separable data.
method Design of efficient algorithms based on kernel Perceptron for strong and weak linear separability conditions.
result Near-optimal mistake bounds of $O\left( K/γ^2
ight)$ for strong separability and min ( 2 O ~ ( K log 2 ( 1 / γ ) ) , 2 O ~ ( 1 / γ log K ) ) \min (2^{\widetilde{O}(K \log^2 (1/γ))}, 2^{\widetilde{O}(\sqrt{1/γ} \log K)}) min ( 2 O ( K l o g 2 ( 1/ γ )) , 2 O ( 1/ γ l o g K ) ) for weak separability. ETGP improves multi-class classification efficiency.
problem Efficiently handling non-stationary, dependent multi-class classification problems.
method ETGP uses transformed Gaussian processes with efficient sparse variational inference.
result ETGPs outperform state-of-the-art methods in multi-class classification tasks.
Efficient multi-class classification with well-calibrated uncertainty.
problem Trade-off between uncertainty calibration and speed in multi-class Gaussian process classification.
method Proposes a new likelihood function leading to a conditionally conjugate model with efficient variational inference.
result Up to two orders faster than state-of-the-art methods with well-calibrated uncertainty estimates.
New linear models improve time series classification efficiency and interpretability.
problem Complex and inefficient classifiers limit interpretability and applicability to variable-length time series.
method Symbolic representations, multi-resolution, multi-domain, linear models.
result mtSS-SEQL+LR achieves similar accuracy to state-of-the-art methods but with lower time and memory usage.
FrequentNet uses frequency domain basis vectors for image classification, making models more interpretable and efficient.
problem Image classification models are often complex and hard to interpret.
method FrequentNet selects filter vectors from frequency domain basis vectors instead of training them with back propagation.
result The method improves interpretability and efficiency of image classification models.
Paper explores reducing precision in SVM for faster text classification.
problem Efficiency in multi-class text classification training.
method Comparison of SVM trained with reduced precision (16-bit, half) vs original.
result Reduced precision training maintains text classification accuracy.
Improved multivariate time series classification models.
problem Multivariate time series classification challenges.
method Transformed LSTM-FCN and ALSTM-FCN into multivariate models.
result Proposed models outperform state-of-the-art models.
sktime toolkit benchmarks time series classification algorithms for correctness and efficiency.
problem Benchmarking correctness and efficiency of time series classification algorithms.
method Implementation and comparison of six classifiers in sktime with their tsml equivalents.
result Significant differences in accuracy and efficiency between algorithms, with one causing debugging issues.
Paper presents an efficient algorithm for learning minimax risk classifiers with large-scale data.
problem Efficient learning of minimax risk classifiers for large-scale data with multiple classes.
method Combination of constraint and column generation for efficient learning.
result 10x speedup for general large-scale data and 100x speedup with many classes.
A new algorithm efficiently selects features for functional data classification.
problem Feature selection and classification of functional data in high-dimensional spaces.
method Developed a novel optimization problem integrating logistic loss and functional features. Employed functional principal components and a new adaptive Dual Augmented Lagrangian algorithm for efficient minimization.
result FSFC outperforms other methods in computational time and classification accuracy.
Efficient algorithm for clustering and classification using MBO scheme.
problem Data clustering and classification tasks.
method Introduces constraints on cluster size leading to a linear integer problem, proving it's induced by a novel order statistic. Develops exact and efficient algorithms based on variational viewpoint connecting to volume-preserving mean curvature flow.
result Estimates computational complexity better than state-of-the-art, proving rigorous analysis.
Directly compute classification by learning features with class scores.
problem Classification efficiency and accuracy on various datasets.
method PCA for feature encoding, supervised learning model with encoder-decoder structure.
result Effective classification performance on multiple datasets.
Study shows computational limits for robust classification tasks, leading to cryptographic implications.
problem Computational limitations in learning robust classifiers for classification tasks.
method Extending previous work on statistical/computational tradeoffs, using average-case hard functions and one-way functions.
result Computational hardness of learning robust classifiers even when efficient non-robust classifiers exist.
Paper reduces neural network complexity for image classification.
problem High computational complexity in deep neural networks.
method Proposes a two-step classification process: coarse-grain and fine-grain.
result Achieves similar accuracy with less computational complexity.
Develops an online federated learning framework for classification.
problem Handling streaming data from multiple clients while ensuring data privacy and efficiency.
method Leverages generalized distance-weighted discriminant technique and Majorization-Minimization principle.
result Achieves high classification accuracy, significant computational efficiency, and data security enhancements.
Efficiently predicts paths in hierarchical text classification using unlabeled data.
problem Costly labeling of documents in hierarchical text classification.
method Path cost-sensitive learning algorithm using generative model and path constraints.
result Significantly reduces computational cost and improves efficiency.
Proposes DCADL for efficient image classification with reduced complexity.
problem Efficiency and discriminative capability in DL methods for image classification.
method Jointly learns a convolutional analysis dictionary and a universal classifier, reducing time complexity.
result Achieves competitive accuracy with reduced computational cost.
Paper proposes AdaBoost-assisted ELM for efficient online sequential classification.
problem Efficient online sequential classification with improved accuracy and stability.
method Utilizes AdaBoost for cost-sensitive learning and forgetting mechanism for stability.
result Achieves 94.41% accuracy on MNIST dataset with reduced standard deviation.
r-STSF improves TSC accuracy and interpretability.
problem Lack of interpretability in state-of-the-art TSC methods.
method Randomized-Supervised Time Series Forest (r-STSF) using interval-based approach and ensemble of randomized trees.
result r-STSF achieves state-of-the-art accuracy and enables interpretability.
ICE algorithm solves exact 0-1 loss linear classification problem efficiently.
problem Exact solution to the 0-1 loss linear classification problem for non-linearly separable data.
method Incremental cell enumeration (ICE) algorithm, leveraging combinatorial and incidence relations.
result First provably optimal algorithm for exact 0-1 loss linear classification problem.
Randomized classifiers improve strategic classification efficiency.
problem Designing optimal classifiers in strategic classification games.
method Investigation of randomized classifiers and their efficiency in strategic classification.
result Randomized classifiers are necessary for maximizing classification efficiency.
Energy-efficient detection of natural errors in deep networks.
problem Deep networks lack error detection capability without additional energy costs.
method Append RACs at hidden layers to detect natural errors with early classification termination.
result Early classification termination reduces energy consumption.
MSNet uses high frequency residual learning for efficient multi-scale image classification.
problem Efficient multi-scale image classification for mobile and embedded devices.
method Two network architecture: low resolution for low frequency, high resolution for high frequency residuals.
result MSNet achieves significant accuracy improvements over different base networks.
Classifiers based on sparse representations have recently been shown to provide excellent results in many visual recognition and classification tasks. However, the high cost of computing sparse representations at test time is a major obstacle that limits the applicability of these methods in large-scale problems, or in…
Study shows a tradeoff between sample complexity and computational efficiency for learning halfspaces with random noise.
problem PAC learning γ-margin halfspaces with Random Classification Noise.
method Established an information-computation tradeoff and provided a simple efficient algorithm with sample complexity O(1/(γ^2 ε^2)). Also, proved lower bounds for SQ algorithms and low-degree polynomial tests.
result Inherent gap between sample complexity and computational efficiency for learning halfspaces with random noise.
Efficient text classification model reduces size and speeds up inference.
problem Label-scarce conditions in text classification.
method Convolutional student architecture trained by distillation from a transformer teacher.
result 300x inference speedup and 39x reduction in parameter count.
Due to myriads of classes, designing accurate and efficient classifiers becomes very challenging for multi-class classification. Recent research has shown that class structure learning can greatly facilitate multi-class learning. In this paper, we propose a novel method to learn the class structure for multi-class clas…
Enhanced EEG classification improves motor imagery detection with less computation.
problem Improving classification accuracy of motor imagery EEG signals.
method Integrates Block-Toeplitz structure into augmented covariance matrices and uses Siegel metric.
result Significantly reduces computational time without compromising classification accuracy.
Efficient neural network ensembles improve image classification reliability and uncertainty quantification.
problem Uncertainty in neural network predictions for industrial image classification.
method Investigated efficient neural network ensembles (snapshot, batch, multi-input multi-output) for image classification reliability and uncertainty quantification.
result Batch ensemble is a cost-effective and competitive alternative to deep ensembles, offering savings in training and test time.
Efficiently models categorical data with low to medium class overlap, improving accuracy over standard distributions.
problem Poor parameter estimates and accuracy in multinomial and Dirichlet multinomial distributions when assumptions are violated.
method Introduces Beta-Liouville multinomial distribution and efficient estimation methods.
result Beta-Liouville multinomial outperforms standard distributions on two out of four datasets.
New algorithms improve time series classification accuracy and efficiency while enhancing interpretability.
problem Lack of interpretability in time series classification algorithms.
method Combining multiple resolutions and domains, using SEQL with greedy feature selection.
result SAX-SFA-SEQL achieves similar accuracy to state-of-the-art methods but with lower computational time.
Proposes a spiking neural network for efficient classification.
problem High computational and power costs of ANNs.
method Random Neural Network (RNN) with spiking neurons.
result Matches classification power of ANNs but with lower energy consumption.