Improved VQA accuracy with generalized fusion operators.
problem Enhancing multimodal fusion for better VQA performance.
method Generalized Hadamard-Product fusion operators with Nonlinearity Ensembling, Feature Gating, and post-fusion layers.
result 1.1% absolute improvement on VQA 2.0 test-dev set.
SemiNAS reduces NAS cost by predicting accuracy of unlabeled architectures.
problem Costly evaluation of architectures limits NAS efficiency.
method SemiNAS uses unlabeled architectures to train an accuracy predictor.
result SemiNAS achieves comparable accuracy with less data.
Paper benchmarks causal discovery techniques based on accuracy of inference.
problem Comparing causal discovery algorithms for accuracy of inference tasks.
method Categorized algorithms into two categories and compared them on three perspectives: structural accuracy, standard predictive accuracy, and counterfactual inference.
result Structural accuracy does not correlate with inferencing accuracy, and algorithms perform poorly with many variables.
Proposes a new adversarial model to avoid accuracy vs. adversarial accuracy tradeoff.
problem Inherent tradeoff between accuracy and adversarial accuracy in existing adversarial robustness definitions.
method Introduces Voronoi-epsilon adversary that balances perturbation constraints.
result Voronoi-epsilon adversary avoids accuracy vs. adversarial accuracy tradeoff even with large ε. Selective classification can worsen accuracy disparities between groups.
problem Selective classification can magnify existing accuracy disparities between various groups.
method Study of margin distribution and distributionally-robust models.
result Selective classification can uniformly improve each group on distributionally-robust models.
Calibrated ensembles improve both ID and OOD accuracy in distribution shift.
problem Desired balance between in-distribution and out-of-distribution accuracy.
method Ensemble standard and robust models, calibrating on ID data only.
result ID-calibrated ensembles outperform state-of-the-art methods on multiple datasets.
Paper monitors DNN accuracy to enhance trustworthiness.
problem Varying DNN accuracy in practice and lack of ground truth labels.
method Post-hoc accuracy monitor model using Monte-Carlo dropout ensemble.
result Accuracy monitor provides close-to-true accuracy estimation.
Adversarial training can degrade standard accuracy even when optimal for robust accuracy.
problem Tradeoff between standard and robust accuracy in adversarial training.
method Analyzes adversarial training's impact on standard accuracy, even when optimal for robust accuracy.
result Even with optimal predictors, adversarial training can still degrade standard accuracy.
Optimizes glmnet configuration for better accuracy and efficiency.
problem Inappropriate glmnet configuration leads to inaccurate solutions and increased computation time.
method Data-driven framework using neural networks to predict accuracy and computation time from dataset characteristics and configuration.
result Automatic selection of optimal configuration maximizing accuracy under a time constraint.
Online learning improves big data accuracy quickly.
problem Heterogeneity in big data analysis.
method Online machine learning for big data.
result Online learning converges quickly to batch accuracy.
Machine learning can predict cancer with 100% accuracy on a dataset.
problem Accuracy of cancer predictions using machine learning.
method Extensive experiments on the Wisconsin Diagnostic Breast Cancer dataset.
result Machine learning algorithms can be easily misled to achieve 100% accuracy.
TRUST improves tree models' accuracy while maintaining interpretability.
problem Piecewise-constant regression trees lack in predictive accuracy compared to black-box models.
method Combines Random Forest accuracy with interpretability of shallow trees and sparsity of linear models, using LLMs for explanations.
result TRUST outperforms other interpretable models in predictive accuracy and matches Random Forest's accuracy.
FADE framework improves fairness and accuracy in ensemble learning.
problem Improving fairness in existing models without sacrificing accuracy.
method Flexible fair ensemble learning framework targeting multiple fairness criteria.
result Multiple unfairness measures can be minimized simultaneously with little impact on accuracy.
Paper explores tradeoff between standard and robust accuracy for latent models.
problem Tradeoff between standard accuracy and robust accuracy in adversarial training.
method Revisits adversarial training for latent models, considering Gaussian mixture and generalized linear models.
result Low-dimensional manifold structure mitigates the tradeoff between standard and robust accuracy.
Patch Gaussian augmentation improves model robustness without sacrificing accuracy.
problem Challenges in building robust models without sacrificing accuracy.
method Adds Gaussian noise to randomly selected patches in images.
result Achieves state-of-the-art performance on benchmarks while improving clean data accuracy.
New methods show robustness and accuracy can coexist.
problem Inevitability of robustness-accuracy tradeoff in deep learning.
method Prove robustness and accuracy achievable through locally Lipschitz functions; explore combining dropout with robust training methods.
result Achieving robustness and accuracy requires methods imposing local Lipschitzness and deep learning generalization techniques.
Improved forecast accuracy for Knitwear by 20% using adaptive AI/ML model.
problem Low accuracy in demand forecasts for Knitwear product category.
method Dynamic selection of the best algorithm from an algorithm rack based on performance and context.
result Increased forecast accuracy from 60% to 80% for Knitwear.
Proposes an accuracy-preserving calibration method for DNNs.
problem Calibration of deep neural networks (DNNs) to measure prediction reliability.
method Uses Concrete distribution on the probability simplex to calibrate DNNs without accuracy loss.
result The proposed method outperforms previous methods in accuracy-preserving calibration tasks.
Improves natural accuracy of deep learning models by combining robust predictions and features.
problem Maintaining natural accuracy while resisting adversarial attacks.
method Ensemble methods combining robust and standard models.
result Optimized natural accuracy through ensemble of robust models.
New method improves deep RL efficiency by adaptively setting accuracy requirements.
problem Improving efficiency in deep reinforcement learning.
method Accuracy-based curriculum learning using adaptive selection of accuracy requirements.
result Adaptive accuracy requirements lead to better learning efficiency than random selection.
The paper studies and mitigates accuracy disparity in regression models.
problem Accuracy disparity between different demographic subgroups in high-stakes domains.
method Error decomposition theorem and distribution alignment algorithm.
result The proposed algorithm effectively mitigates accuracy disparity while maintaining predictive power.
New work shows limits of certifying neural network robustness.
problem Certified training improves robustness but decreases accuracy.
method Bayes error analysis to investigate robustness limits.
result Upper bound for certified robust accuracy established.
The paper analyzes adversarial training effects on classification accuracy.
problem Understanding adversarial training's impact on standard and robust accuracy.
method Derived precise statistical analysis for binary classification problems with Gaussian data.
result Theoretical explanation of standard and robust accuracy trends for adversarial training.
Project fair estimators while maintaining accuracy.
problem Making estimators fair without sacrificing accuracy.
method Optimal transport tools to find closest fair estimator.
result Efficiently constructs fair estimators with quantified cost.
Network Implosion reduces ResNet layers without accuracy loss.
problem High computation costs in Residual Networks.
method Static layer pruning and retraining to erase unimportant layers.
result Reduces ResNet layers by 24.00-42.86% without accuracy drop.
Empirical law predicts accuracy of Google Translate's translation chains.
problem Predicting accuracy in machine translation with multiple hops.
method Empirical testing of Google Translate's sequential translation.
result Accuracy decreases with the number of translating hops, following a power law.
New research shows no trade-off between fairness and accuracy in machine learning.
problem The trade-off between fairness and accuracy in machine learning is a widely accepted belief.
method Using mismatched hypothesis testing and Chernoff information, the study demonstrates that optimal fairness and accuracy can be achieved simultaneously.
result There is no inherent trade-off between fairness and accuracy in ideal distributions, but it exists when measured with respect to biased datasets.
Learning ReLU networks to high uniform accuracy requires exponentially many samples.
problem Achieving high uniform accuracy on ReLU networks for security-critical applications.
method Quantified the number of training samples needed for any algorithm to guarantee uniform accuracy.
result The minimal number of training samples scales exponentially with network depth and input dimension.
MobileNet CNN achieves high accuracy in skin disease classification on Android.
problem Skin disease classification using smartphone technology.
method Transfer learning on MobileNet, imbalanced dataset handling (sampling and preprocessing), and data augmentation.
result Oversampling and data augmentation on preprocessing input data achieved 94.4% accuracy.
BitPruning learns optimal bitlengths for neural networks to balance accuracy and efficiency.
problem Finding the minimum bitlength for neural network accuracy.
method A training method that penalizes large bitlengths and minimizes other quantifiable criteria.
result The method learns efficient representations while maintaining accuracy, reducing bitlengths by 3.76 bits on average per layer.
The paper examines how adversarial robustness affects accuracy disparity across different classes.
problem Understanding the impact of adversarial robustness on accuracy disparity across different classes.
method Linear classifiers under a Gaussian mixture model, decomposing the impact into inherent and imbalance effects.
result Adversarial robustness consistently degrades standard accuracy in balanced classes, but the class imbalance ratio plays a different role in accuracy disparity.
APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.
problem Efficient deep learning inference on resource-constrained hardware.
method Joint optimization of neural architecture, pruning, and quantization policy using a quantization-aware accuracy predictor.
result Joint optimization leads to 2.3% higher ImageNet accuracy with reduced latency and energy consumption.
Unhinged loss minimization fails to improve classifier accuracy for simple data.
problem Accuracy of classifiers minimizing the unhinged loss.
method Minimizing the unhinged loss function.
result Minimizing the unhinged loss yields classifiers with accuracy no better than random guessing for simple data.
New accuracy measure Ha improves AI system assessment in clinical practice.
problem Inadequate metrics for assessing AI system performance in clinical settings.
method Introducing H-accuracy (Ha) as a more informative measure.
result H-accuracy is a generalization of balanced accuracy and related to Net Benefit.
Accuracy on in-distribution data correlates with out-of-distribution data when data is noisy or contains nuisance features.
problem Correlation between in-distribution and out-of-distribution accuracy in noisy or feature-rich data.
method Analyzes the impact of noise and nuisance features on model performance.
result Accuracy on in-distribution and out-of-distribution data can become negatively correlated in noisy or feature-rich data.
New definition shows no trade-off between adversarial and standard accuracy.
problem Inexact definition of adversarial perturbation causes confusion.
method Proposed a slight modification to adversarial perturbation definition.
result Existence of classifiers that are robust and achieve high standard accuracy.
Paper analyzes trade-offs in top-k classification accuracies and proposes a new loss function.
problem CE loss does not always optimize top-k prediction, especially with complex data.
method Introduces a novel top-k transition loss to improve top-k accuracy.
result Our loss function improves top-k accuracy, especially for k > 10.
Paper introduces a method to control early classification accuracy gaps.
problem Maintaining accuracy in early classification without full input processing.
method Statistical framework for a calibrated stopping rule.
result Reduces up to 94% of timesteps while controlling accuracy gaps.
Linear trends in classifier accuracy observed under distribution shift.
problem Understanding why classifier accuracies show linear trends under distribution shift.
method Assumed model similarity and verified empirically.
result Linear trend in classifier accuracy occurs unless distribution shift is large.
Paper improves classification accuracy using synthetic data and probabilistic models.
problem Low classification accuracy in supervised learning algorithms.
method Using probabilistic mixture models to identify sub-labels and generate synthetic data.
result Better classification accuracy achieved through synthetic data generation.
Researchers study fairness-accuracy tradeoffs in predictive models for multiple groups.
problem Understanding the tradeoff between fairness and accuracy in models serving multiple demographic groups.
method Characterizing the fairness-accuracy (FA) Pareto frontier, approximating it from limited data, and bounding the worst-case gap.
result Derivation of worst-case-optimal estimators and uniform finite-sample bounds for the entire FA frontier.
TIP-Search optimizes market prediction accuracy and timeliness under uncertain load.
problem Real-time market prediction requires accurate predictions before a deadline.
method Filters feasible models, dispatches workers, trades accuracy for deadline risk.
result Optimized pool achieves 0.991 timely accuracy and 0.994 raw accuracy.
Removing spurious features can hurt model accuracy and disproportionately affect different groups.
problem Interference from spurious features in robust model performance across different groups.
method Characterization and analysis of spurious feature removal in noiseless overparameterized linear regression.
result Removal of spurious features can decrease accuracy and disproportionately affect different groups, even in balanced datasets.
New method preserves both benign and robust accuracy in deep neural networks.
problem Large neural networks have high computational and storage costs.
method Pruning with fine-tuning to preserve both benign and robust accuracy.
result Average 93% benign accuracy, 92.5% empirical robust accuracy, and 85.0% verifiable robust accuracy preserved while compressing by 10x.
The paper discusses thresholds and bounds for accuracy in binary classification systems.
problem The accuracy of binary classification systems and its dependence on prevalence.
method Analyzing the precision-prevalence curve and negative predictive value-prevalence curve to find thresholds and bounds.
result Thresholds (φe and φn) bound various accuracy metrics (Fβ, F1, FM, MCC) and the ratio of maximum accuracy to prevalence. New test set shows drop in CIFAR-10 classifier accuracy.
problem Questioning the reliability of current machine learning accuracy numbers.
method Created a new test set of unseen images from CIFAR-10.
result Drop in accuracy from 4% to 10% for deep learning models.
Deep learning models' architectures, including depth and width, are key factors influencing models' performance, such as test accuracy and computation time. This paper solves two problems: given computation time budget, choose an architecture to maximize accuracy, and given accuracy requirement, choose an architecture …
Enhances k-NN accuracy through randomized hyperstructure.
problem Improves k-NN accuracy by optimizing neighbor selection.
method Constructs a random n-dimensional hyperstructure around test instances to refine neighbor selection.
result 85.71% accuracy on Haberman's Cancer Survival dataset, compared to 80.95% for conventional k-NN.