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.
Discriminator guidance improves autoregressive diffusion models for generating molecular graphs.
Study on GANs under and overfitting using discriminator unseen data.
Pairwise discriminators stabilize adversarial training by ensuring the generator's alignment is preserved.
PBN combines generative and discriminative capabilities in a neural network.
Solves GAN mode collapse by assigning minibatches to multiple discriminators.
Generalized dual discriminator GANs improve upon traditional GANs by using two discriminators and a flexible loss function.
We study two important concepts in adversarial deep learning---adversarial training and generative adversarial network (GAN). Adversarial training is the technique used to improve the robustness of discriminator by combining adversarial attacker and discriminator in the training phase. GAN is commonly used for image ge…
New method computes discriminative classifiers from generative models.
Generative Adversarial Networks (GANs) can successfully approximate a probability distribution and produce realistic samples. However, open questions such as sufficient convergence conditions and mode collapse still persist. In this paper, we build on existing work in the area by proposing a novel framework for trainin…
Abstract: Analogs of Hilbert-Chow morphism for generalized discriminants.
Lower-dimensional video discriminators improve GAN performance.
The standard practice in Generative Adversarial Networks (GANs) discards the discriminator during sampling. However, this sampling method loses valuable information learned by the discriminator regarding the data distribution. In this work, we propose a collaborative sampling scheme between the generator and the discri…
Kernel discriminant analysis uses nonlinear embeddings to improve classification.
Naive Bayes can be used as a discriminative classifier, matching the definition of logistic regression.
Smart Bayes integrates generative and discriminative features for improved classification.
Paper introduces a new method to improve GANs by leveraging the discriminator's energy.
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 …
Discriminative classifier for compositional data using hierarchical mixture of Generalized Dirichlet models.
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…
Discriminator optimizes to approximate optimal transport for better image generation.
We study Bayesian discriminative inference given a model family $p(c,\x, θ)$ that is assumed to contain all our prior information but still known to be incorrect. This falls in between "standard" Bayesian generative modeling and Bayesian regression, where the margin $p(\x,θ)$ is known to be uninformative about $p(c|\x,…
Discrimination-aware classification is receiving an increasing attention in data science fields. The pre-process methods for constructing a discrimination-free classifier first remove discrimination from the training data, and then learn the classifier from the cleaned data. However, they lack a theoretical guarantee f…
DNLL loss improves deep LDA accuracy and consistency.
A new method removes policy optimization in adversarial imitation learning.
Proposes a sparse classifier for discriminative Gaussian Mixture Models.
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 …
Recent work has shown that exploiting relations between labels improves the performance of multi-label classification. We propose a novel framework based on generative adversarial networks (GANs) to model label dependency. The discriminator learns to model label dependency by discriminating real and generated label set…
Generative Adversarial Networks (GANs) are one of the most popular tools for learning complex high dimensional distributions. However, generalization properties of GANs have not been well understood. In this paper, we analyze the generalization of GANs in practical settings. We show that discriminators trained on discr…
GAN-based semi-supervised learning improves classifier generalization.
We empirically characterize the performance of discriminative and generative LSTM models for text classification. We find that although RNN-based generative models are more powerful than their bag-of-words ancestors (e.g., they account for conditional dependencies across words in a document), they have higher asymptoti…
Discriminators can be good feature extractors despite their task focus.
Study shows infoGAN's generalization error bound for two-layer networks.
WGANs improve probability distribution approximation with depth and width trade-offs.
Discriminative clustering uses mutual information to cluster data.
IDVAE combines VAE and GAN without explicit discriminator.
Simplified GAN model shows how discriminator improves generalization.
New method optimizes kernel feature maps for better classification.
Study infinite Euclidean distance discriminants of algebraic varieties.
Generative adversarial networks (GANs) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminator usually as- sesses individual samples. This prevents the dis- criminator from accessing global distributional statistics of generated samp…
Paper formalizes anti-discrimination law in automated systems.
We propose to incorporate adversarial dropout in generative multi-adversarial networks, by omitting or dropping out, the feedback of each discriminator in the framework with some probability at the end of each batch. Our approach forces the single generator not to constrain its output to satisfy a single discriminator,…
The two key players in Generative Adversarial Networks (GANs), the discriminator and generator, are usually parameterized as deep neural networks (DNNs). On many generative tasks, GANs achieve state-of-the-art performance but are often unstable to train and sometimes miss modes. A typical failure mode is the collapse o…
We show that, for generative classifiers, conditional independence corresponds to linear constraints for the induced discrimination functions. Discrimination functions of undirected Markov network classifiers can thus be characterized by sets of linear constraints. These constraints are represented by a second order fi…
Optimized GAN discriminator using polyharmonic interpolation.
AdvAs improves GAN training by penalizing the generator based on discriminator gradients.
SONA improves conditional generation by balancing authenticity and alignment.
We propose in this paper a novel approach to tackle the problem of mode collapse encountered in generative adversarial network (GAN). Our idea is intuitive but proven to be very effective, especially in addressing some key limitations of GAN. In essence, it combines the Kullback-Leibler (KL) and reverse KL divergences …
Generative adversarial nets (GANs) are a promising technique for modeling a distribution from samples. It is however well known that GAN training suffers from instability due to the nature of its maximin formulation. In this paper, we explore ways to tackle the instability problem by dualizing the discriminator. We sta…