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.
Technical report on f-divergences and f-GAN training properties.
Generative adversarial networks (GANs) have enjoyed much success in learning high-dimensional distributions. Learning objectives approximately minimize an -divergence (-GANs) or an integral probability metric (Wasserstein GANs) between the model and the data distribution using a discriminator. Wasserstein GANs en…
Improves Bridge estimators using f-GAN to minimize RMSE.
The paper analyzes the statistical properties of GANs using -divergence.
There has recently been a steady increase in the number iterative approaches to density estimation. However, an accompanying burst of formal convergence guarantees has not followed; all results pay the price of heavy assumptions which are often unrealistic or hard to check. The Generative Adversarial Network (GAN) lite…
Robust estimation under Huber's -contamination model has become an important topic in statistics and theoretical computer science. Statistically optimal procedures such as Tukey's median and other estimators based on depth functions are impractical because of their computational intractability. In this paper, we est…
In this note, we point out a basic link between generative adversarial (GA) training and binary classification -- any powerful discriminator essentially computes an (f-)divergence between real and generated samples. The result, repeatedly re-derived in decision theory, has implications for GA Networks (GANs), providing…
Generative adversarial networks are a novel method for statistical inference that have achieved much empirical success; however, the factors contributing to this success remain ill-understood. In this work, we attempt to analyze generative adversarial learning -- that is, statistical inference as the result of a game b…
Unified framework for generative models incorporating VAE and GAN.
Generative adversarial network (GAN) is a minimax game between a generator mimicking the true model and a discriminator distinguishing the samples produced by the generator from the real training samples. Given an unconstrained discriminator able to approximate any function, this game reduces to finding the generative …
Since the introduction of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAE), the literature on generative modelling has witnessed an overwhelming resurgence. The impressive, yet elusive empirical performance of GANs has lead to the rise of many GAN-VAE hybrids, with the hopes of GAN level perfor…
Nowozin \textit{et al} showed last year how to extend the GAN \textit{principle} to all -divergences. The approach is elegant but falls short of a full description of the supervised game, and says little about the key player, the generator: for example, what does the generator actually converge to if solving the GAN…
Study extends DRO with IPMs, linking robustness to regularization and GANs.
New theory explains GAN's high quality but low diversity.
Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights. These models are expressive and allow efficient computation of samples and derivatives, but …
A new GAN model -GAN with tunable loss function addresses gradient vanishing and mode collapse issues.
Survey of GANs and autoencoders, addressing mode collapse and likelihood issues.
It is important to collect credible training samples for building data-intensive learning systems (e.g., a deep learning system). Asking people to report complex distribution , though theoretically viable, is challenging in practice. This is primarily due to the cognitive loads required for human agents t…
We introduce a new approximation of -divergences for machine learning.
Paper introduces a new method to improve GANs by leveraging the discriminator's energy.
Improved GAN training stability through tunable classification losses.
Generative adversarial networks (GANs) can be interpreted as an adversarial game between two players, a discriminator D and a generator G, in which D learns to classify real from fake data and G learns to generate realistic data by "fooling" D into thinking that fake data is actually real data. Currently, a dominating …