Study infinite Euclidean distance discriminants of algebraic varieties.
problem Understanding the structure of data points with infinitely many critical points in Euclidean distance correspondence.
method Developed computer code to compute discriminants and proved properties of fibers.
result Infinite Euclidean distance discriminants contain all data points with infinitely many critical points for the nearest-point problem.
Solves GAN mode collapse by assigning minibatches to multiple discriminators.
problem Mode collapse in GANs where models generate similar samples.
method Multiple discriminators, microbatching, and changing tasks.
result Promotes sample diversity in generated sets.
New method studies discriminantal loci of algebraic varieties.
problem Understanding discriminantal loci of algebraic varieties.
method Efficient use of groupoids to describe monodromy.
result New insights into discriminantal loci of hypersurfaces.
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.
Proposes a new GAN framework using adversarial dropout to improve sample diversity and stability.
problem Mode collapse in GANs.
method Adversarial dropout in a dynamic ensemble of discriminators.
result Promotes sample diversity and stabilizes training.
This paper is devoted to the classification of connected components of Prym eigenform loci in the strata H(2,2)^odd and H(1,1,2) in the Abelian differentials bundle in genus 3. These loci, discovered by McMullen are GL^+(2,R)-invariant submanifolds (of complex dimension 3) that project to the locus of Riemann surfaces …
Study on the topology of twistor discriminant loci in 4-sphere.
problem Topology of twistor discriminant loci of algebraic surfaces.
method Classical algebraic geometry techniques applied to twistor fibration.
result Real dimension of twistor discriminant locus is always 2 except for two exceptional cases.
As machine learning is applied to an increasing variety of complex problems, which are defined by high dimensional and complex data sets, the necessity for task oriented feature learning grows in importance. With the advancement of Deep Learning algorithms, various successful feature learning techniques have evolved. I…
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…
Let V be a finite dimensional complex vector space and V^* its dual and let X in P(V) be a smooth projective variety of dimension n and degree d at least two. For a generic n-tuple of hyperplanes H_1,...,H_n in P(V^*)^n, the intersection of X with H_1,...,H_n consists of d distinct points. We define the "discriminant o…
A new method removes policy optimization in adversarial imitation learning.
problem Adversarial imitation learning's delicate alternated optimization.
method Explicitly condition discriminator on two policies, solving generator's optimization problem directly.
result Simpler approach competitive to prevalent methods.
The study examines higher-order modern portfolio theory with complex critical points and feasible portfolio variety.
problem Understanding the complex critical points and feasible portfolio variety in higher-order modern portfolio theory.
method Established genericity conditions for utility functions with higher-order cumulants, analyzed discriminant loci, and determined the dimension and degree of the feasible portfolio variety.
result The utility function has a constant number of complex critical points under genericity conditions, and the feasible portfolio variety has a determined dimension and degree.
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold and higher energies to other regions. Similar to the probabilistic GANs, a generator is seen as being trained to produce con…
A variety of real-world tasks involve the classification of images into pre-determined categories. Designing image classification algorithms that exhibit robustness to acquisition noise and image distortions, particularly when the available training data are insufficient to learn accurate models, is a significant chall…
Study data biases to predict algorithmic discrimination, developing a Data Bias Profile.
problem Data biases contribute to algorithmic discrimination, but their impact is understudied.
method Analyzed three common data biases across various datasets and models, developing a Data Bias Profile.
result Combination of proxies and label bias can lead to more significant discrimination than underrepresentation alone.
We introduce a graphical framework for multiple instance learning (MIL) based on Markov networks. This framework can be used to model the traditional MIL definition as well as more general MIL definitions. Different levels of ambiguity -- the portion of positive instances in a bag -- can be explored in weakly supervise…
New CGAN technique for efficient constrained topology design.
problem Constrained topology optimization with high computational cost.
method Conditional GAN (crCGAN) with deep CNNs and relaxed formulations.
result Improved efficiency and accuracy in topology design.
Wasserstein GANs are shown to have hidden convexity, enabling exact solutions with convex optimization.
problem Non-convex and non-concave optimization in GANs.
method Convex duality analysis of Wasserstein GANs with two-layer neural network discriminators.
result Wasserstein GANs can be solved exactly with convex optimization under certain conditions.
The Kalman filter (KF) is used in a variety of applications for computing the posterior distribution of latent states in a state space model. The model requires a linear relationship between states and observations. Extensions to the Kalman filter have been proposed that incorporate linear approximations to nonlinear m…
The paper proves a theorem and characterizes connections over normal varieties.
problem The study addresses the stability and connections over normal varieties.
method The authors prove a complete version of the Donaldson-Uhlenbeck-Yau theorem and use it to show the polystability of reflexive sheaves.
result An admissible Hermitian-Yang-Mills connection defines a polystable reflexive sheaf and gives a lower bound for discriminants.
Paper tackles expected predictions computation for arbitrary generative models.
problem Hard to compute expected predictions for arbitrary generative models.
method Identifies tractable generative and discriminative models for expected predictions.
result Tractable computation of high-order moments and expectations for classification.
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.
Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a gene…
GraphGAN unifies generative and discriminative models for graph representation learning.
problem Learning effective graph representations from graph data.
method GraphGAN uses a minimax game between a generative and a discriminative model.
result GraphGAN outperforms state-of-the-art methods in various graph tasks.
Improves deep generative model samples via gradient flow.
problem Inconsistent generation quality across samples.
method Discriminator Gradient Flow (DGflow) using entropy-regularized f-divergences.
result Significant improvement in generated sample quality.
INK scores improve OOD detection for classifiers.
problem Detecting out-of-distribution inputs for classification models.
method INK scores operate on constrained latent embeddings modeled as a mixture of hyperspherical embeddings, optimizing in modern neural networks.
result INK establishes a new state-of-the-art in OOD detection.
New method trains generative models without discriminators, improving stability and accuracy.
problem Training implicit generative models with adversarial discriminators leads to instability and mode-dropping.
method Invariant statistical loss function, avoiding discriminators.
result Successfully trains generative models for various complex distributions without mode-dropping.
LDA-GO improves LDA for high-dimensional data via gradient optimization.
problem LDA struggles in high-dimensional settings due to unreliable covariance matrix estimation.
method LDA-GO learns a low-rank precision matrix via gradient optimization, automatically selecting between Gaussian likelihood and cross-entropy loss.
result LDA-GO outperforms other LDA variants in sparse-signal high-dimensional regimes.
Generative model improves ECG classification with limited data.
problem Poor performance of RNNs with limited channel ECG data.
method Generative Seq2Seq model to fill missing data, followed by discriminative learning.
result Generative approach outperforms standard RNNs in disease prediction.
In this paper, we classify three-dimensional complex Abelian varieties isogenous to a product A1×A2, where one of the factors admits real multiplication by a real quadratic order OD of discriminant D. We show that the moduli space XD(3) of these varieties essentially is the disjoint unio…
New method combines deep learning and streaming learning for better incremental learning.
problem Catastrophic forgetting in deep neural networks when updated incrementally.
method Combining streaming linear discriminant analysis with deep learning.
result Outperforms incremental batch learning and streaming learning on ImageNet and CORe50.
In this paper we study output coding for multi-label prediction. For a multi-label output coding to be discriminative, it is important that codewords for different label vectors are significantly different from each other. In the meantime, unlike in traditional coding theory, codewords in output coding are to be predic…
Discriminative neural networks address class imbalance in coronary heart disease risk analysis.
problem Class imbalance in medical test data, especially in binary classification problems.
method Use of discriminative neural networks and contrastive loss with a Siamese network structure.
result The method effectively handles class imbalance, improving predictive models for coronary heart disease risk.
Paper explores optimizing GANs' latent space without adversarial training.
problem Understanding the role of saddle point optimization and deep neural networks in GANs.
method Introduces Generative Latent Optimization (GLO) to train deep convolutional generators using simple reconstruction losses.
result GLO achieves desirable GAN properties (synthesizing samples, interpolating, arithmetic with noise) without adversarial training.
Study uses EEG features HFD and SampEn to detect depression with high accuracy.
problem Diagnosing depression reliably and accurately.
method Applied Higuchi Fractal Dimension and Sample Entropy on EEG signals using seven machine learning algorithms.
result Good classification possible even with small EEG data, achieving high accuracy.
Sparse coding improves reinforcement learning representations.
problem Improving representation learning in reinforcement learning.
method Developed a supervised sparse coding objective for policy evaluation.
result Sparse coding representations outperform tile-coding representations.
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.
ControlGAN improves GANs by generating detailed, specific features.
problem Current GANs struggle with generating detailed, specific features.
method ControlGAN separates a feature classifier from a discriminator to generate detailed features.
result ControlGAN generates improved samples with well-controlled features.
For high-dimensional classification, it is well known that naively performing the Fisher discriminant rule leads to poor results due to diverging spectra and noise accumulation. Therefore, researchers proposed independence rules to circumvent the diverse spectra, and sparse independence rules to mitigate the issue of n…
Framework learns sentence order from paragraphs using attention and transformer networks.
problem Learning to order sentences from a paragraph.
method Bidirectional sentence encoder and self-attention transformer network for ranking.
result Framework outperforms state-of-the-art methods on sentence ordering and discrimination tasks.
Mining discriminative subgraph patterns from graph data has attracted great interest in recent years. It has a wide variety of applications in disease diagnosis, neuroimaging, etc. Most research on subgraph mining focuses on the graph representation alone. However, in many real-world applications, the side information …
VCL combines online VI and Monte Carlo VI for neural networks.
problem Catastrophic forgetting in continual learning.
method Fuses online variational inference and Monte Carlo VI.
result VCL outperforms state-of-the-art methods on various tasks.
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.
EOI enhances individuality in multi-agent systems.
problem Improving multi-agent cooperation through individuality.
method A probabilistic classifier that predicts agent identity based on observations, with intrinsic rewards and regularizers.
result EOI significantly outperforms existing methods in multi-agent cooperative scenarios.
Deep Sets improve jet discrimination in particle physics.
problem Representing and learning from collider events with variable-length particle sets.
method Energy Flow Networks and Particle Flow Networks, based on Deep Sets framework.
result Improved or similar performance in discriminating quark jets from gluon jets compared to existing methods.
A set of probabilistic predictions is well calibrated if the events that are predicted to occur with probability p do in fact occur about p fraction of the time. Well calibrated predictions are particularly important when machine learning models are used in decision analysis. This paper presents two new non-parametric …
Paper improves matrix-valued data classification using nonparametric LDA.
problem Classification of matrix-valued data in neuroimaging and signal processing.
method Nonparametric LDA based on NPMLE for vectorized and scaled matrices.
result Improves classification performance across various data structures.
FineHand learns hand shapes for better ASL recognition.
problem Difficult ASL recognition due to fast, articulate gestures.
method Combines manual and deep learning for hand shape embeddings, uses RNN for sequential gestures.
result Improved video gesture recognition accuracy on GMU-ASL51 benchmark.