Paper formalizes anti-discrimination law in automated systems.
problem Algorithmic discrimination in legal contexts.
method Decision-theoretic framework grounded in UK anti-discrimination law.
result Introduced 'conditional estimation parity' metric for ML fairness.
This article guides data scientists on avoiding discrimination in machine learning.
problem Machine learning systems can create or exacerbate societal disparities.
method Provides a taxonomy of practices and measures to mitigate discrimination.
result Data scientists should be intentional about modeling and reducing discriminatory outcomes.
Machine learning identifies boundaries of real solutions in polynomial systems.
problem Locating boundaries in parameter space for real solutions of polynomial systems.
method Supervised machine learning approach using nearest neighbor and deep learning approximations.
result Efficiently approximates the real discriminant locus for multidimensional parameter spaces.
Discriminative classifiers improve decision-making in SHM systems.
problem Lack of descriptive labels for SHM data.
method Risk-based active learning with discriminative classifiers.
result Discriminative classifiers offer improved robustness and reduced inspection costs.
Improves model classification accuracy in black-box settings.
problem Difficulty in inferring model properties due to limited query access.
method Introduces discriminative factorization to distinguish high-quality queries.
result Probability of chance-level classification decreases exponentially with query budget.
Improved LID for multilingual speakers using context-aware models.
problem Low accuracy for languages spoken by multilingual speakers, especially with accented speech.
method Coarser-grained acoustic model and integration with interaction context signals.
result Average 97% accuracy across all language combinations, 60% improvement in worst-case accuracy.
GPdoemd optimizes experiments for model discrimination using Gaussian processes.
problem Discriminating between competing models when data is limited.
method Developed a new design criterion and Gaussian process surrogate method for black-box models.
result Demonstrated improved model discrimination using Gaussian process surrogates.
A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown promising results. The extracted frame-level (DNN bottleneck, posterior or d-vector) …
Develops a method to identify nonproperness sets in likelihood-equation systems.
problem Classifying data based on the number of positive critical points of likelihood functions.
method Computes nonproperness sets using a novel method and proves its correctness.
result The method is more efficient than existing methods in the literature.
AI systems can be corrected without rebuilding them, using simple linear methods.
problem Errors in AI systems can lead to serious consequences.
method Developed fast non-destructive methods using linear Fisher discriminant.
result Simple linear methods can separate error-prone situations from correct ones.
Enhances dialogue model with persona attributes using adversarial learning.
problem Improving dialogue models to better capture speaker identity and topic.
method Adversarial learning framework with a dual discriminator system.
result phredGAN outperforms persona Seq2Seq model in various datasets.
Develops a method to discriminate between competing models using Gaussian process surrogates.
problem Discriminating between competing models when data is insufficient and models are non-analytical.
method Introduces Gaussian process surrogates to extend design of experiments methods to non-analytical models.
result Extends design of experiments methods to non-analytical models in a computationally efficient manner.
The paper tackles fairness in supervised learning using information theory.
problem Discrimination in decision rules derived from biased historical data.
method Information theoretic framework for designing fair predictors, using equalized odds criterion.
result Designing predictors that are independent of a sensitive attribute while generalizing well.
Study local convergence of GDA for training GANs with kernel-based discriminators.
problem Analyzing the local dynamics of GDA for GANs with kernel-based discriminators.
method Linearization of a non-linear dynamical system, under an isolated points model assumption.
result Showed phase transitions indicating convergence, oscillation, or divergence of GDA.
New method detects metastable basins in high dimensions using trajectory sampling.
problem Identifying distinct basins in high-dimensional Markov processes.
method Discriminative approach based on marginal trajectory distribution comparison.
result Bayes-optimal classifier achieves high accuracy distinguishing between basins.
Proposes KMvDA for object recognition from multi-view data.
problem Recognizing objects from different views, even when views are heterogeneous.
method Introduces kernel multi-view discriminant analysis (KMvDA) and uses random Fourier features (RFF) for large-scale learning.
result KMvDA and RFF approximation improve object recognition from multi-view data.
Defends against adversarial attacks using GANs by leveraging both discriminator and generator.
problem Vulnerability of state-of-the-art models to adversarial perturbations.
method Uses a GAN's discriminator and generator to detect and defend against adversarial samples.
result Adversarial samples lie outside the data manifold learned by the GAN.
The paper tackles fairness in algorithmic decision making using causal models.
problem Ensuring algorithmic decision making systems do not discriminate based on protected attributes.
method Introduces two definitions of group fairness (FACE and FACT) grounded in causal models and uses Rubin-Neyman potential outcomes framework for robust estimation.
result Demonstrates the effectiveness of FACE and FACT in detecting discrimination in real-world data sets.
fairmodels tool detects and mitigates bias in machine learning models.
problem Bias in machine learning models leading to discrimination.
method Model-agnostic approach to bias detection, visualization, and mitigation.
result Validates fairness and eliminates bias in classification models.
A brain computer interface (BCI) is a system which provides direct communication between the mind of a person and the outside world by using only brain activity (EEG). The event-related potential (ERP)-based BCI problem consists of a binary pattern recognition. Linear discriminant analysis (LDA) is widely used to solve…
The study redefines algorithmic fairness as a sociotechnical concept.
problem Systemic discrimination in automated decision-making.
method Literature review and sociotechnical analysis.
result Algorithmic fairness should be viewed through a sociotechnical lens.
The paper improves safety in autonomous systems using adversarial learning.
problem Ensuring safety in real-time control systems of autonomous vehicles.
method The paper introduces a dual anomaly detection framework (CFAM and SFAM) using generative adversarial networks (GANs) and video prediction.
result Demonstrated effectiveness on both indoor and outdoor autonomous ground vehicles.
New training method for ASR models reduces word error rate.
problem Traditional ASR training methods do not directly optimize word error rate.
method Training attention-based models to minimize expected word error rate using N-best lists.
result Improved performance by up to 8.2% compared to baseline.
The paper tackles selective labels in decision making, proposing a data augmentation approach to mitigate bias and discrimination.
problem Selective labels cause bias in decision making, making standard bias correction methods ineffective.
method Proposes a data augmentation approach to leverage expert consistency or empirically validate models under selective labels.
result Data augmentation can mitigate the bias caused by selective labels and prevent unreliable models.
This study examines methods for detecting dataset shifts in ML systems.
problem Detecting and warning about unexpected inputs in ML systems.
method Investigated methods for detecting dataset shift, including two-sample testing and domain discrimination.
result A two-sample testing-based approach using pre-trained classifiers for dimensionality reduction performs best.
We present a new, far simpler family of counter-examples to Kushnirenko's Conjecture. Along the way, we illustrate a computer-assisted approach to finding sparse polynomial systems with maximally many real roots, thus shedding light on the nature of optimal upper bounds in real fewnomial theory. We use a powerful recen…
Deep learning models can discriminate against certain groups, requiring computational methods to ensure fairness.
problem Algorithmic discrimination in deep learning models affecting protected groups.
method Interpretability and mitigation approaches at different stages of deep learning lifecycle.
result Interpretability aids in diagnosing and mitigating algorithmic discrimination in deep learning.
Hybrid method improves mutual information estimation from samples.
problem Estimating mutual information from joint distributions is challenging.
method Proposes a hybrid method combining discriminative and generative approaches.
result Hybrid methods yield tighter variational bounds on mutual information.
Improved deep neural networks for text-independent speaker recognition.
problem Text-independent speaker recognition using deep neural networks.
method Angular softmax activation, residual frame level connections, cosine similarity, discriminative similarity metric learning.
result Improved speaker recognition accuracy on real-life conditions.
xAI-GAN improves GANs by providing richer feedback, enhancing image quality.
problem Challenges in GAN training, especially resource-intensive and data-intensive.
method Integrates xAI systems to provide richer corrective feedback from discriminators to generators.
result Improves image quality by up to 23.18% on MNIST and FMNIST datasets.
Local discovery method uncovers direct unfairness in complex systems.
problem Identifying causal pathways of unfairness in complex domains.
method Local discovery for direct discrimination (LD3) method.
result LD3 returns a valid adjustment set (VAS) for assessing unfairness.
Study shows neural networks outperform traditional methods in speaker identification.
problem Open-set speaker identification with large populations.
method Discriminative neural networks compared to Gaussian mixture models.
result Multi-class neural networks outperform traditional methods for large speaker populations.
The AAA credit rating may have been overly precise given available data.
problem The feasibility of achieving high reliability targets for structured credit products.
method Bayes' theorem and historical data analysis.
result High reliability targets for structured products require substantial statistical discrimination, which was not achievable with available data.
Improved RA detection with SNN outperforming baseline by 26.8% EER.
problem Improving RA detection systems' generalizability and discriminability.
method Multi-task learning with Siamese Neural Networks (SNN) and additional reconstruction loss.
result SNN outperforms baseline by 26.8% EER, and further improvement by 13.8% with reconstruction loss.
Representing examples in a way that is compatible with the underlying classifier can greatly enhance the performance of a learning system. In this paper we investigate scalable techniques for inducing discriminative features by taking advantage of simple second order structure in the data. We focus on multiclass classi…
Method identifies key features for clustering in high-dimensional data.
problem Understanding hidden patterns in high-dimensional data.
method Unsupervised feature selection based on discriminative power.
result 27 key transcription factors identified, 18 known to define cell states.
Monodromy and vanishing cycles computed for ample linear systems on simply connected surfaces.
problem Characterizing curves that can be vanishing cycles in degenerations of linear systems.
method Computing mapping class group-valued monodromy and identifying it with r-spin mapping class groups.
result Identifies simple closed curves as vanishing cycles and provides characterizations of discriminants and Lefschetz fibrations.
FedGAN trains GANs across distributed data sources with reduced communication.
problem Training GANs across non-independent data sources with privacy and communication constraints.
method FedGAN uses local generators and discriminators synced via an intermediary, proving convergence under standard assumptions.
result FedGAN converges and performs similarly to general distributed GANs with reduced communication complexity.
Study uses neural networks to detect nonlinear dynamics in short time series.
problem Challenges in testing dynamical nonlinearities in short time series.
method Recurrent neural network classification framework using raw time series data.
result Classifier accuracy is higher than 50% for chaotic processes, around 50% for nonlinearly correlated noise.
Study shows improving information content in risk scores can reduce algorithmic discrimination.
problem Algorithmic prediction systems may discriminate against underrepresented populations.
method Investigates the role of information in fair prediction, introduces refinement concept.
result Improving information content through refinements improves downstream selection rules and reduces disparity in treatment.
Study uses DHS to classify anemia types using CBC indices.
problem Anemia classification for medical purposes.
method Dynamic Harmony Search (DHS) applied to CBC indices.
result DHS outperforms other models in anemia classification.
Paper proposes fair decision trees to avoid unfair treatment.
problem Discriminative decision-making in automated systems.
method Mixed-integer optimization framework for fair decision trees.
result Improves fairness and accuracy in decision-making.
FAHT improves fairness in online decision-making systems.
problem Discrimination in decision support systems due to biased data.
method FAHT is an adaptive fairness-aware decision tree classifier based on Hoeffding Tree algorithm.
result FAHT maintains fairness while maintaining moderate predictive performance in streaming environments.
Study improves speaker verification accuracy using angular based embedding learning.
problem Improving discriminative power of embeddings for open-set speaker verification.
method Optimizes angular distance and adds margin penalty, applying various angular margin embedding strategies and proposing inter-class regularization.
result Achieved impressive results with 16.5% improvement in EER and 18.2% improvement in minimum detection cost function.
The study quantifies and compares aleatoric and epistemic discrimination in ML models.
problem Sources of discrimination in ML models and their impact on performance.
method Quantifying aleatoric and epistemic discrimination using statistical experiments and model accuracy.
result State-of-the-art fairness interventions are effective at removing epistemic discrimination but not aleatoric discrimination in datasets with missing values.
Paper proposes DCDG for semi-supervised learning with MRI data.
problem Lack of labeled data and distribution mismatch between labeled and unlabeled data.
method Double-sided domain adaptation for feature space fusion and indirect learning for discriminativeness.
result Proposed DCDG achieves compelling segmentation results for LGE-CMRI images.
A new algorithm balances fairness in clustering to avoid discrimination.
problem Clustering data can unfairly discriminate against different demographic groups.
method Designing a stochastic alternating balance fair k-means algorithm (SAfairKM) that alternates between k-means updates and group swap updates.
result The algorithm efficiently constructs well-spread and high-quality Pareto fronts on synthetic and real datasets.
The paper highlights legal misunderstandings in ML fairness definitions.
problem Misalignment between ML fairness definitions and legal concepts.
method Examples and comparative analysis of legal and ML terminology.
result Both communities need to learn from these tensions.