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.
AdaPID optimizes diffusion-based samplers by dynamically adjusting schedules.
Bilinear models such as DistMult and ComplEx are effective methods for knowledge graph (KG) completion. However, they require large batch sizes, which becomes a performance bottleneck when training on large scale datasets due to memory constraints. In this paper we use occurrences of entity-relation pairs in the datase…
Generative Adversarial Networks (GANs) are a powerful class of generative models. Despite their successes, the most appropriate choice of a GAN network architecture is still not well understood. GAN models for image synthesis have adopted a deep convolutional network architecture, which eliminates or minimizes the use …
This paper improves Bayesian inference for predictive models with limited data.
Improved diffusion models for sampling from given distributions.
We focus on generative autoencoders, such as variational or adversarial autoencoders, which jointly learn a generative model alongside an inference model. Generative autoencoders are those which are trained to softly enforce a prior on the latent distribution learned by the inference model. We call the distribution to …
Generative Adversarial Networks (GANs) have achieved great success in generating realistic images. Most of these are conditional models, although acquisition of class labels is expensive and time-consuming in practice. To reduce the dependence on labeled data, we propose an un-conditional generative adversarial model, …
Achieving faster execution with shorter compilation time can enable further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional compilation heuristics, or very recently, simulated annealing and genetic algorithms.…
Score matching method improves image generation quality.
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,…
This paper introduces a new method to train normalizing flows using precision-recall divergences.
Improves diffusion models by controlling total variance and signal-to-noise-ratio.
Improved sampling quality with RBM-Flow and D-Flow models.
In this work, we empirically explore the question: how can we assess the quality of samples from some target distribution? We assume that the samples are provided by some valid Monte Carlo procedure, so we are guaranteed that the collection of samples will asymptotically approximate the true distribution. Most current …
Improves sample efficiency and generalization in vision-based RL by enhancing exploration.
The computational cost of training with softmax cross entropy loss grows linearly with the number of classes. For the settings where a large number of classes are involved, a common method to speed up training is to sample a subset of classes and utilize an estimate of the loss gradient based on these classes, known as…
A new method learns continuous guidance weights to improve diffusion model quality and distributional alignment.
VBS improves sampling efficiency in cosmological data analysis.
PNDMs accelerate DDPMs by treating them as differential equations on manifolds.
D-Wave quantum annealing fails to improve sampling quality from RBMs compared to Gibbs sampling.
We propose flow-based likelihoods to accurately capture non-Gaussian data.