Metrics specifying distances between data points can be learned in a discriminative manner or from generative models. In this paper, we show how to unify generative and discriminative learning of metrics via a kernel learning framework. Specifically, we learn local metrics optimized from parametric generative models. T…
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 “discriminative metrics”
We define an integer-valued non-degenerate bi-invariant metric (the discriminant metric) on the universal cover of the identity component of the contactomorphism group of any contact manifold. This metric has a very simple geometric definition, based on the notion of discriminant points of contactomorphisms. Using gene…
New findings show fixed-kernel discriminators are weaker than feature-learning ones.
problem Comparing performance of fixed-kernel and feature-learning discriminators.
method Using function classes and , constructing pairs of distributions, and linking IPMs with sliced Wasserstein distances.
result Fixed-kernel IPM and SD cannot discriminate certain distributions that feature-learning IPM and SD can.
We consider a pseudo-Riemannian metric that changes signature along a smooth curve on a surface, called the discriminant curve. The discriminant curve separates the surface locally into a Riemannian and a Lorentzian domain. We study the local behaviour and properties of geodesics at a point on the discriminant where th…
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.
Survey of spectral, probabilistic, and deep metric learning methods.
problem Developing effective distance metrics for various machine learning tasks.
method Divided into spectral, probabilistic, and deep approaches, covering various techniques and their applications.
result Comprehensive overview of metric learning methods, including new developments and applications.
This paper analyzes implicit bias in Deep Linear Discriminant Analysis.
problem The implicit bias of Deep Linear Discriminant Analysis.
method Analyzing gradient flow on a L-layer diagonal linear network.
result Under balanced initialization, the network transforms additive updates into multiplicative updates, conserving the (2/L) quasi-norm.
Study local models for special Kähler metrics near discriminant locus components.
problem Analyzing singularities of special Kähler metrics along discriminant locus of Hitchin base.
method Computed Taylor expansion, defined subsystems, and analyzed asymptotics and convergence of metrics.
result Logarithmic asymptotics in transversal directions and convergence to a metric on strata.
A new metric DJP-MMD improves domain adaptation by balancing transferability and discriminability.
problem Improving domain adaptation performance by balancing transferability and discriminability.
method Discriminative Joint Probability Maximum Mean Discrepancy (DJP-MMD) replaces the traditional joint MMD.
result DJP-MMD outperforms traditional MMDs in image classification tasks.
New metrics improve quantum ensemble learning efficiency and power.
problem Quantum ensembles' distances poorly understood due to measurement constraints.
method Introduce MMD- hierarchy of integral probability metrics for quantum ensembles.
result MMD- requires fewer samples for full discriminative power at higher .
New robustness metric helps select reliable classifiers.
problem Evaluating reliability of classifier predictions.
method Proposed new robustness metric for any classifier and feature type.
result Demonstrated ability to distinguish reliable from unreliable predictions.
The paper studies 8D manifolds with a specific tensor field called a cubic discriminant.
problem Characterizing and understanding 8D Riemannian manifolds with reduced structure groups.
method Introducing an almost quaternion-Hermitian structure and a cubic discriminant tensor field.
result Only two non-flat, integrable examples of these structures are found: quaternion-Kähler symmetric spaces.
The paper calculates the Saito determinant for Coxeter discriminant strata.
problem Calculating the Saito determinant for specific geometric strata.
method Using the Saito flat metric and Lie derivatives, the paper finds the determinant of the metric restricted to Coxeter discriminant strata.
result The determinant of the Saito metric on Coxeter discriminant strata is proportional to a product of linear factors in flat coordinates.
Distributive Justice and Fairness Metrics in Automated Decision-making: How Much Overlap Is There?stat.ML
The paper explores fairness metrics in automated decision-making and their limitations.
problem Discrimination in automated resource allocation decisions.
method Analysis of fairness metrics and distributive justice principles.
result Prominent fairness metrics fail to address egalitarian and sufficiency concerns in resource allocation.
Paper introduces negative margin loss for better few-shot classification accuracy.
problem Improving few-shot classification accuracy with metric learning.
method Introduces negative margin loss and analyzes its impact on feature discriminability.
result Negative margin loss outperforms regular softmax loss on few-shot classification benchmarks.
Study of twisted Kähler-Einstein metrics on Calabi-Yau spaces with singularities.
problem Understanding the collapsed Gromov-Hausdorff limits of Calabi-Yau spaces.
method Analyzing the geometry of twisted Kähler-Einstein metrics on holomorphic fiber spaces.
result Proving the existence of conical-type singularities in the base of fiber spaces.
Proposes a framework to improve domain adaptation without labeled data.
problem Improving adaptability and preserving intrinsic data structure in unsupervised domain adaptation.
method Discriminative Manifold Propagation framework using soft labels and manifold metric alignment.
result The method achieves better transferability and discriminability compared to existing approaches.
Improved covariance estimation for various metrics outperforms existing methods.
problem Estimating covariance and precision matrices for a wide range of metrics.
method Random matrix theory for improved estimation.
result Significantly outperforms sample covariance matrix and state-of-the-art methods.
Paper proposes SDRL to improve continual learning with less computational cost.
problem Catastrophic forgetting in continual learning.
method SDRL method that refines gradients from memorized samples to reduce gradient diversity.
result SDRL shows better performance than state-of-the-art methods on multiple benchmark tasks.
Generalized dual discriminator GANs improve upon traditional GANs by using two discriminators and a flexible loss function.
problem Mode collapse in GANs.
method Introducing dual discriminator -GANs and extending the approach to arbitrary functions.
result The approach reduces the optimization problem to a linear combination of an -divergence and a reverse -divergence.
This study examines how well GANs estimate the Wasserstein metric.
problem Estimating the Wasserstein metric from samples in GANs.
method Analyzes -transform formulation to improve Wasserstein metric estimation.
result The -transform does not perform best in the generative setting.
Generative adversarial training can be generally understood as minimizing certain moment matching loss defined by a set of discriminator functions, typically neural networks. The discriminator set should be large enough to be able to uniquely identify the true distribution (discriminative), and also be small enough to …
We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN). The discriminator of an LD-GAN is trained to maximize the linear separability between distributions of hidden representations of generated and targeted samples, while the …
A distributed approach for efficient metric learning.
problem Efficiently learning metrics for large datasets.
method Discriminative metric learning on subsets, then aggregating results.
result ADML achieves state-of-the-art performance at lower computational cost.
Simplified GAN model shows how discriminator improves generalization.
problem Understanding GAN's generalization ability and avoiding memorization.
method Analyzing a simplified GAN model with early stopping and Wasserstein metric.
result Generalization error escapes from curse of dimensionality with early stopping.
New approach stabilizes GANs by leveraging implicit competitive regularization.
problem Stability issues in GAN training due to discriminator's exploitation of generator errors.
method Competitive Gradient Descent (CGD) for opponent-aware modeling of generator and discriminator.
result Significant improvement in GAN training stability without explicit regularization.
A new IPM uses ReLU networks to measure probability discrepancies.
problem Measuring the difference between two probability distributions in high dimensions.
method Proposes a new parametric IPM using ReLU neural networks to optimize and distinguish between distributions.
result The proposed IPM has good convergence rates and can be used as a surrogate for other IPMs.
We study the interplay between sequential decision making and avoiding discrimination against protected groups, when examples arrive online and do not follow distributional assumptions. We consider the most basic extension of classical online learning: "Given a class of predictors that are individually non-discriminato…
In this paper, we present an algorithm for minimizing the difference between two submodular functions using a variational framework which is based on (an extension of) the concave-convex procedure [17]. Because several commonly used metrics in machine learning, like mutual information and conditional mutual information…
Paper introduces a new method to improve GANs by leveraging the discriminator's energy.
problem Improving the quality of generated samples in GANs.
method Discriminator Contrastive Divergence (DCD) method.
result Significant improvement in generation quality on synthetic and real-world data.
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
problem Evaluation of GANs for sample quality and diversity.
method Integrates various factors including intra-class and inter-class diversity, disentanglement, and discriminability metrics.
result Demonstrates improved evaluation of GANs on MNIST dataset.
Given a compact polarized Kähler manifold , the space of Bergman metrics on , parameterized by , corresponds to a dense set in the space of Kähler potentials in the Kähler class as . Critical points of the th K-energy functional, which is def…
Develops RES metrics for stable rare-event forecasting evaluation.
problem Challenges in evaluating forecasts of rare events.
method Rare-event-stable (RES) metrics designed to maintain stable thresholds under extreme rarity.
result RES metrics maintain stable thresholds, consistent model rankings, and near-complete prevalence invariance.
Explains LDA and QDA for binary and multiple classes.
problem Classification methods in statistical and probabilistic learning.
method Optimization of decision boundaries, estimation of parameters, relation to other methods.
result Equivalence of LDA and Fisher discriminant analysis.
A Discriminative Deep Forest (DisDF) as a metric learning algorithm is proposed in the paper. It is based on the Deep Forest or gcForest proposed by Zhou and Feng and can be viewed as a gcForest modification. The case of the fully supervised learning is studied when the class labels of individual training examples are …
A new method for unsupervised domain adaptation using manifold learning.
problem Leveraging rich source domain information to target domain without labeled data.
method Discriminative Manifold Embedding and Alignment framework.
result Consistent transferability and discriminability achieved through manifold metric alignment.
Paper introduces new loss functions for Siamese networks using FDA.
problem Training Siamese networks with improved loss functions.
method Proposes Fisher Discriminant Triplet (FDT) and Fisher Discriminant Contrastive (FDC) loss functions based on FDA.
result Shows effectiveness of FDT and FDC on MNIST and histopathology datasets.
One of the most fundamental problems in machine learning is to compare examples: Given a pair of objects we want to return a value which indicates degree of (dis)similarity. Similarity is often task specific, and pre-defined distances can perform poorly, leading to work in metric learning. However, being able to learn …
New algorithm reduces discrimination in predictions.
problem Tackles potential discrimination in AI predictions.
method Integrates fairness adjustments into tree-building process.
result Reduces discriminatory predictions without significant loss in accuracy.
While Generative Adversarial Networks (GANs) have empirically produced impressive results on learning complex real-world distributions, recent works have shown that they suffer from lack of diversity or mode collapse. The theoretical work of Arora et al. suggests a dilemma about GANs' statistical properties: powerful d…
Discriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detectioncs.LG
DCAE learns compact latent representations for one-class novelty detection.
problem Learning compact latent representations for one-class novelty detection.
method DCAE learns compact and collapse-free latent representations through internal discriminative layers of GANs, reconstructing in-class data finely and exclusively.
result DCAE achieves state-of-the-art performance on novelty and adversarial example detection.
We present Generative Adversarial Capsule Network (CapsuleGAN), a framework that uses capsule networks (CapsNets) instead of the standard convolutional neural networks (CNNs) as discriminators within the generative adversarial network (GAN) setting, while modeling image data. We provide guidelines for designing CapsNet…
Study evaluates human vs. machine review generation, finds human assessments correlate better with lexical overlaps.
problem Evaluating natural language generation models for online reviews is challenging and inconsistent.
method Compared human evaluators with various automated evaluation methods, including discriminative and word overlap metrics.
result Human evaluators do not correlate well with discriminative evaluators, but correlate better with lexical overlaps.
New LFR algorithm ensures fair predictions with theoretical guarantees.
problem Ensuring fairness in AI algorithms for social decision-making.
method Proposes a new adversarial training scheme using IPM with a parametric family of discriminators.
result Theoretical guarantee of fairness in final prediction models.
Study of Calabi-Yau metrics on converging manifolds, resolving conjectures.
problem Understanding Calabi-Yau metrics on converging manifolds.
method Analysis of Gromov-Hausdorff limits of metrics on Calabi-Yau fibrations.
result Gromov-Hausdorff limit is homeomorphic to the base of the fibration and discriminant locus has high Hausdorff codimension.
We introduce a novel discriminative latent variable model for bilingual lexicon induction. Our model combines the bipartite matching dictionary prior of Haghighi et al. (2008) with a representation-based approach (Artetxe et al., 2017). To train the model, we derive an efficient Viterbi EM algorithm. We provide empiric…
KM-GAN generates images without labels using K-Means and GANs.
problem Reducing label dependence in GANs for efficient image generation.
method KM-GAN integrates K-Means clustering into GANs' framework for feature extraction and updates.
result KM-GAN generates high-quality images comparable to conditional GANs.
The paper explores theoretical insights into WGANs for better understanding and stability.
problem Stabilizing the training process of GANs.
method Theoretical analysis and statistical convergence study of WGANs.
result Theoretical properties and convergence of WGANs are clarified.