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.
Empirical study shows GANs overfit and drop modes when training is deterministic.
NS-GAN mode collapse due to sample weighting inversion, solved with MM-nsat.
Study on stability of 3D sessile drops, identifying degenerate kernel.
This paper introduces a new method to train normalizing flows using precision-recall divergences.
GANs mode collapse solved with Bures distance.
Despite excellent progress in recent years, mode collapse remains a major unsolved problem in generative adversarial networks (GANs).In this paper, we present spectral regularization for GANs (SR-GANs), a new and robust method for combating the mode collapse problem in GANs. Theoretical analysis shows that the optimal …
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,…
MsIGN tackles high-dimensional Bayesian inference using multiscale structure.
Cautious Weight Decay modifies weight decay for better optimization.
New method trains generative models without discriminators, improving stability and accuracy.
FDS tackles long horizon hyperparameter optimization issues.
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…
VINNAS uses variational inference to avoid mode collapse in neural architecture search.
Evaluating generative adversarial networks (GANs) is inherently challenging. In this paper, we revisit several representative sample-based evaluation metrics for GANs, and address the problem of how to evaluate the evaluation metrics. We start with a few necessary conditions for metrics to produce meaningful scores, su…
Unified ML and adversarial learning via α-divergence.
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…
AGF explains feature learning in neural networks through alternating steps.
Training generative adversarial networks requires balancing of delicate adversarial dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with dropped modes. In this work, we improve CS-GAN with natural gradient-based latent optimisation and show that it improves adversarial dynamics b…
Method diagnoses model performance under distribution shifts.
Round balls minimize liquid drop model volumes ≤ 1.
Unconditional image generation has recently been dominated by generative adversarial networks (GANs). GAN methods train a generator which regresses images from random noise vectors, as well as a discriminator that attempts to differentiate between the generated images and a training set of real images. GANs have shown …
The 2006 sudden and immense downturn in U.S. House Prices sparked the 2007 global financial crisis and revived the interest about forecasting such imminent threats for economic stability. In this paper we propose a novel hybrid forecasting methodology that combines the Ensemble Empirical Mode Decomposition (EEMD) from …
Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activation functions by setting them to be identity functions randomly during training time. During testing, …
The study examines mass drop and multiplicity in mean curvature flow.
We improve generative models for heavy-tailed multivariate data using an invariant statistical loss.
This paper analyzes the configurations of shapes that shows a spacelike liquid drop in Minkowski space deposited over a spacelike plane . We assume the presence of a uniform gravity field directed toward and that the volume of the drop is prescribed. Our interest are the liquid drops that are critical points of …
Improves DPGMM sampler by better initializing subclusters for more effective clustering.
Deep neural networks have dramatically achieved great success on a variety of challenging tasks. However, most successful DNNs have an extremely complex structure, leading to extensive research on model compression.As a significant area of progress in model compression, traditional gradual pruning approaches involve an…
KSGAN uses KS distance for deep generative modeling.
Deep neural networks are vulnerable to adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performance of defense techniques still lags behind. This paper proposes ME-Net, a defense method that leverages matrix estimation (ME). In ME-Net, i…
Deep neural networks (DNNs) have been proven to have many redundancies. Hence, many efforts have been made to compress DNNs. However, the existing model compression methods treat all the input samples equally while ignoring the fact that the difficulties of various input samples being correctly classified are different…
Paper resolves Huisken's conjecture without strict genus drop theorem.
Study on liquidation games with market drop-out, proving unique equilibria.
TinyML models detect RF and cyber threats in spacecraft with low latency.
LC-CRFs are equivalent to HMMs, and MPM/MAP classifiers can be reformulated as CRFs.
Periodic surfaces have a limited number of bending modes, equal to their membrane modes.
Natural images may lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative Adversarial Networks (GANs). In this work, we first show that single generator GANs are unable to correctly model a distribution supported on…
Sparse-mode DMD disambiguates local and global modes in spatiotemporal data.
Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes. Unfortunately, using large batches is slow and expensive on conventional hardware. Thus, it would be nice if we could generate batches that were effectively large though actual…
Recent advances in generative modeling have led to an increased interest in the study of statistical divergences as means of model comparison. Commonly used evaluation methods, such as the Frechet Inception Distance (FID), correlate well with the perceived quality of samples and are sensitive to mode dropping. However,…
Motivated by advantages of current-mode design, this brief contribution explores the implementation of weight matrices in neuromemristive systems via current-mode memristor crossbar circuits. After deriving theoretical results for the range and distribution of weights in the current-mode design, it is shown that any we…
RDIS fills missing values in time series data explicitly.
Study on how reparametrization affects neural nets' parameter spaces from a geometric perspective.
The Frank-Wolfe (FW) algorithm has been widely used in solving nuclear norm constrained problems, since it does not require projections. However, FW often yields high rank intermediate iterates, which can be very expensive in time and space costs for large problems. To address this issue, we propose a rank-drop method …
For dynamical systems that can be modelled as asymptotically stable linear systems forced by Gaussian noise, this paper develops methods to infer or estimate their modes from observations in real time. The modes can be real or complex. For a real mode, we wish to infer its damping rate and mode shape. For a complex mod…
Study connects hyperbolic geometry to membrane shapes.
Characterizes neutral deformation modes of minimal surfaces.
In this paper we compare market price fluctuations with the response to fundamental price drops within the Lux-Marchesi model which is able to reproduce the most important stylized facts of real market data. Major differences can be observed between the decay of spontaneous fluctuations and of changes due to external p…