This paper offers a mathematical introduction to GANs.
problem Understanding GANs from a mathematical perspective.
method Mathematical analysis of GANs.
result Provides clarity for math-oriented students.
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 “generative adversarial nets (GANs)”
We show that training of generative adversarial network (GAN) may not have good generalization properties; e.g., training may appear successful but the trained distribution may be far from target distribution in standard metrics. However, generalization does occur for a weaker metric called neural net distance. It is a…
GANs have hidden assumptions causing practical issues.
problem GANs' practical performance contradicts theoretical guarantees.
method Proposed an alternative method to avoid these issues.
result Alternative method sidesteps the identified problems.
Class labels have been empirically shown useful in improving the sample quality of generative adversarial nets (GANs). In this paper, we mathematically study the properties of the current variants of GANs that make use of class label information. With class aware gradient and cross-entropy decomposition, we reveal how …
Paper finds the best way to estimate neural net distance from samples.
problem Estimating the neural net distance from samples.
method Developed minimax lower and upper bounds for the neural net distance.
result Lower and upper bounds match, validating the empirical neural net distance.
We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines optimal transport in primal form with an energy distance define…
DAL uses disentanglement for automatic labeling in GAN-based active learning.
problem Reducing human labeling in GAN-based active learning.
method DAL leverages disentanglement in InfoGAN to automatically label datapoints, deciding human labeling based on disagreement with InfoGAN labels and label correction.
result DAL achieves better performance than existing GAN-based active learning approaches on image classification tasks.
Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original motivation is changed to obtain stronger gradients when learning the generator. We propose a novel algorithm that repeats the density ratio e…
New method uses GANs and proper scoring rules for robust scatter estimation.
problem Robust scatter estimation in statistics.
method General learning via classification framework based on proper scoring rules.
result Proposed robust scatter estimators achieve minimax rate under Huber's contamination model.
Paper presents a new method to avoid mode collapse in implicit generative models.
problem Training implicit generative models is challenging due to mode collapse issues.
method Introduces a learning by teaching (LBT) approach to optimize KL-divergence instead of JS-divergence.
result Optimal generator matches the true data distribution, avoiding mode collapse.
Geometric GANstat.ML
Generative Adversarial Nets (GANs) represent an important milestone for effective generative models, which has inspired numerous variants seemingly different from each other. One of the main contributions of this paper is to reveal a unified geometric structure in GAN and its variants. Specifically, we show that the ad…
Generative models create paintings that match training data.
problem Creating realistic paintings using machine learning.
method Used Spectral Normalization GAN (SN-GAN) and SN-GAN with Gradient Penalty to generate paintings.
result SN-GAN produced paintings most comparable to the training dataset.
ZK-GanDef uses GANs to defend against adversarial examples without using them during training.
problem Adversarial examples challenge the effectiveness of neural network classifiers.
method Generative adversarial net (GAN) based zero knowledge adversarial training defense.
result Enhances test accuracy on adversarial examples by up to 49.17% compared to zero knowledge approaches.
RODE-Net learns ODEs from data with random parameters using neural networks and GANs.
problem Learning ODEs from data with unknown and random parameters.
method RODE-Net combines symbolic networks and GANs to estimate both the ODE and its parameters.
result RODE-Net can accurately estimate the distribution of model parameters and make reliable predictions.
HW2MP-GAN tackles ancient handwritten text recognition.
problem Automatic text recognition from ancient handwritten records.
method Conditional Generative Adversarial Network (HW2MP-GAN) with Sliced Wasserstein distance and U-Net architectures.
result HW2MP-GAN outperforms state-of-the-art models in image-to-image translation and handwritten recognition.
Paper proposes GANs for generating business process suffixes and remaining times.
problem Generating accurate suffixes and remaining times for business process models.
method Encoder-decoder GAN architecture with Gumbel-Softmax distribution for categorical sequences.
result The approach outperforms baselines in suffix and remaining time prediction accuracy.
GanDef uses GANs to defend against adversarial examples in neural networks.
problem Defending against adversarial examples in neural networks.
method GAN-based adversarial training defense using a competition game to regulate feature selection.
result GanDef trains a classifier to defend against adversarial examples with high accuracy.
Dualing GANscs.LG
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…
CounteRGAN generates realistic, actionable counterfactuals for machine learning models.
problem Creating realistic and actionable counterfactuals for machine learning models.
method Applying Residual GANs to improve counterfactual realism and actionability.
result CounteRGAN produces counterfactuals with improved realism and actionability, achieving real-time applicability.
New method generates adversarial examples with conditional GAN.
problem Vulnerability of deep neural networks to adversarial examples.
method Conditional Generative Adversarial Network (cGAN) for generating adversarial examples.
result Our models reduce generating cost and improve robustness.
Generative Adversarial Networks create synthetic PNRs for airline industry.
problem Creating realistic synthetic Passenger Name Records without infringing data ownership laws.
method Cramér GANs, categorical feature embedding, Cross-Net architecture.
result Generated PNRs match real data well and can be used for business applications.
CGAN simulates time series data using categorical and continuous auxiliary info.
problem Simulating time series data with conditional information.
method Conditional Generative Adversarial Net (CGAN) for learning and generating time series data.
result CGAN can learn and generate various time series distributions and structures.
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 …
Lipschitz GANs solve gradient uninformativeness in GANs.
problem Gradient uninformativeness in GANs.
method Introduce Lipschitz constraint on the discriminative function space.
result Lipschitz GANs eliminate gradient uninformativeness and generate better quality samples.
FCC-GAN combines fully connected and convolutional layers for improved GAN performance.
problem Lack of understanding in choosing GAN network architectures.
method Proposes FCC-GAN, a hybrid architecture combining fully connected and convolutional layers.
result FCC-GAN outperforms traditional GAN architectures in terms of learning speed and sample quality.
Researchers use GANs to infer physics-based inverse problems, quantifying uncertainty and promoting generalizability.
problem Quantifying uncertainty in physics-based inverse problems.
method Trained conditional Wasserstein GANs with U-Net architecture and conditional instance normalization.
result The approach effectively samples from the posterior and promotes generalizability with out-of-distribution samples.
Triplet networks are widely used models that are characterized by good performance in classification and retrieval tasks. In this work we propose to train a triplet network by putting it as the discriminator in Generative Adversarial Nets (GANs). We make use of the good capability of representation learning of the disc…
Generative model for inferring graph from time series data.
problem Generating graphs conditioned on multivariate time series data.
method Time Series Conditioned Graph Generation-Generative Adversarial Networks (TSGG-GAN).
result Demonstrates effectiveness and generalizability of TSGG-GAN on synthetic and real-world datasets.
Generative Adversarial Network (GAN) and its variants exhibit state-of-the-art performance in the class of generative models. To capture higher-dimensional distributions, the common learning procedure requires high computational complexity and a large number of parameters. The problem of employing such massive framewor…
We propose a novel method for imputing missing data by adapting the well-known Generative Adversarial Nets (GAN) framework. Accordingly, we call our method Generative Adversarial Imputation Nets (GAIN). The generator (G) observes some components of a real data vector, imputes the missing components conditioned on what …
Paper uses DNN-based MoM-GAN to estimate contaminated data distributions.
problem Estimating distributions of data with outliers or contamination.
method Combines GAN and MoM estimation with DNN for modeling.
result DNN-based MoM-GAN achieves better error bounds than other methods.
Deep learning representations of GAN data are like Gaussian mixtures, according to this study.
problem Understanding the statistical nature of deep learning representations of GAN-generated data.
method Using Random Matrix Theory, the study shows that DL representations of GAN data are concentrated random vectors that behave like Gaussian mixtures.
result Deep learning representations of GAN data can be fully described by their first two statistical moments.
A new mechanism for GANs improves text generation by evaluating sub-sequences.
problem Exposure bias and mode collapse in GANs for text generation.
method Segmenting the sequence into sub-sequences and evaluating them individually.
result Significant improvement in text generation models on benchmark data.
Paper uses GAN to predict opioid relapse from social media data.
problem Accurate relapse prediction for opioid addiction.
method Generative Adversarial Networks (GAN) model trained on sentiment images and social influences.
result GAN model predicts relapse better than alternatives, showing relapse is linked to joy and negative emotions.
New GAN design uses conditional independence graphs to improve model-based GANs.
problem Designing model-based GANs using additional information about underlying distribution.
method Study subadditivity properties of probability divergences to design model-based GANs.
result Model-based GANs using neighborhood discriminators provide significant statistical and computational benefits.
A new GAN model uses characteristic functions to improve image generation.
problem Improving stability and diversity in GANs for complex distributions.
method Integrates characteristic functions to compare distributions directly, stabilizes training, and uses auto-encoder structure.
result Proposes RCF-GAN achieving superior image generation and reconstruction.
Paper tackles co-generation with GANs, developing a new algorithm.
problem Inferring the most likely configuration for a subset of variables given the rest.
method Annealed Importance Sampling based Hamiltonian Monte Carlo algorithm.
result Significantly outperforms classical gradient based methods.
We propose a new approach to train the Generative Adversarial Nets (GANs) with a mixture of generators to overcome the mode collapsing problem. The main intuition is to employ multiple generators, instead of using a single one as in the original GAN. The idea is simple, yet proven to be extremely effective at covering …
This work tackles GAN training instability through parallel tempering.
problem Training instability and mode collapse in GANs.
method Introduces a parallel tempering framework to stabilize GAN training.
result Significantly reduces gradient variance and improves training efficiency.
Unified framework for SDMs and GANs with improved sampling and quality.
problem Limitations of SDMs and GANs in achieving fast sampling and high sample quality.
method Introducing a novel SDE named DiffFlow to describe the learning dynamics of SDMs and GANs, and proving the asymptotic optimality and maximal likelihood training scheme.
result Unified framework allows smooth transition between SDMs and GANs with flexible trade-off between sample quality and speed.
TAC-GAN improves image diversity in AC-GAN by minimizing class distribution divergence.
problem Low diversity in AC-GAN's generated samples as class count increases.
method TAC-GAN introduces twin auxiliary classifiers to address class separability issues.
result TAC-GAN effectively minimizes divergence between generated and real data distributions.
Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs) provide impressive image generations from Gaussian white noise, but the underlying mathematics are not well understood. We compute deep convolutional network generators by inverting a fixed embedding operator. Therefore, they do not require to be o…
Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descentcs.LG
Paper proposes LSVGD to stabilize GAN training via Langevin Stein Variational Gradient Descent.
problem Mode collapse and performance deterioration in GAN training.
method Langevin Stein Variational Gradient Descent (LSVGD) incorporating noise to stabilize training.
result LSVGD improves performance and stability of various GAN models.
Change your singer: a transfer learning generative adversarial framework for song to song conversioncs.LG
SCM-GAN converts any song to sound like a different singer.
problem Converting songs to sound like a different artist.
method Transfer learning and GANs to separate vocals and instruments, then convert and merge.
result SCM-GAN improves song conversion metrics by 35% GV and 13% MS.
Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulationcs.CV
Method interprets GAN latent space via latent variable correlation analysis.
problem Understanding the inner workings of GANs.
method Analyzing correlation between latent variables and semantic contents in generated images.
result A method for controllable semantic content generation in GANs.
Survey of GANs and autoencoders, addressing mode collapse and likelihood issues.
problem Addressing mode collapse and likelihood issues in GANs and autoencoders.
method Explains various GAN and autoencoder variants, their applications, and methods to resolve issues.
result Various methods to resolve mode collapse and improve likelihood in GANs and autoencoders.
Paper proposes a GAN-based method for better next event prediction in business processes.
problem Insufficient training data and sub-optimal network configuration limit deep learning approaches to next event prediction.
method Adversarial training framework using Generative Adversarial Networks (GANs) for sequential temporal data.
result The proposed approach achieves at least as good accuracy as non-adversarial methods and outperforms them in accuracy and prediction earliness.
APAC-Net solves high-dimensional stochastic MFGs using neural networks.
problem High-dimensional stochastic mean-field games.
method Alternating population and control neural networks, parameterizing value and density functions.
result Solves up to 100-dimensional MFG problems.