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.
A method merges two pretrained diffusion experts to improve image quality and likelihood.
This paper introduces a new method to train normalizing flows using precision-recall divergences.
The PARAFAC tensor decomposition has enjoyed an increasing success in exploratory multi-aspect data mining scenarios. A major challenge remains the estimation of the number of latent factors (i.e., the rank) of the decomposition, which yields high-quality, interpretable results. Previously, we have proposed an automate…
Accurately estimating uncertainties in neural network predictions is of great importance in building trusted DNNs-based models, and there is an increasing interest in providing accurate uncertainty estimation on many tasks, such as security cameras and autonomous driving vehicles. In this paper, we focus on the two mai…
Statistical inference on graphs is a burgeoning field in the applied and theoretical statistics communities, as well as throughout the wider world of science, engineering, business, etc. In many applications, we are faced with the reality of errorfully observed graphs. That is, the existence of an edge between two vert…
Differentially private GANs improve image privacy without significant quality loss.
We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable t…
New approach for fair graph clustering using semidefinite relaxation.
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, whose explanation quality can be unpredictable. Our method, ExpO, is a hybridization of these approaches that regu…
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack guarantees about their explanation quality. We propose an alternative to these approaches by directly r…
BOiLS optimizes circuit quality using Bayesian optimization.
Framework evaluates quality of synthetic data generated with differential privacy.
Study on sparse recovery with mixed-quality data, establishing sample-size conditions.
A trade-off exists between reconstruction quality and the prior regularisation in the Evidence Lower Bound (ELBO) loss that Variational Autoencoder (VAE) models use for learning. There are few satisfactory approaches to deal with a balance between the prior and reconstruction objective, with most methods dealing with t…
MGLM models all possible language channel factorizations for improved multilingual generation.
To improve the efficiency of Monte Carlo estimation, practitioners are turning to biased Markov chain Monte Carlo procedures that trade off asymptotic exactness for computational speed. The reasoning is sound: a reduction in variance due to more rapid sampling can outweigh the bias introduced. However, the inexactness …
VADD enhances discrete diffusion models by capturing inter-dimensional correlations, improving sample quality.
New method reduces memorization in diffusion models without sacrificing image quality.
The computational complexity of solving nonlinear support vector machine (SVM) is prohibitive on large-scale data. In particular, this issue becomes very sensitive when the data represents additional difficulties such as highly imbalanced class sizes. Typically, nonlinear kernels produce significantly higher classifica…
Dynamic submodular maximization with consistency constraints.
A new method finds diverse near-optimal portfolios using quality-diversity.
Generative Adversarial Networks (GANs) can achieve state-of-the-art sample quality in generative modelling tasks but suffer from the mode collapse problem. Variational Autoencoders (VAE) on the other hand explicitly maximize a reconstruction-based data log-likelihood forcing it to cover all modes, but suffer from poore…
IMM generates high-quality samples in few steps with stable training.
Cluster-DP improves differential privacy in randomized experiments by clustering data.
Unified model improves sampling speed and quality.
New insights into image compression trade-offs with private randomness.
We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show tha…
The paper uses thermodynamics to improve machine learning representation quality.
Improves disentangled representation learning with multi-stage modeling.
Enhances deep kernel learning with stochastic latent variables for better model regularization.
Diffusion models outperform GANs in image synthesis quality.
Adaptive workflow combines fast amortized inference with MCMC for many datasets.
Inference is an integral part of probabilistic topic models, but is often non-trivial to derive an efficient algorithm for a specific model. It is even much more challenging when we want to find a fast inference algorithm which always yields sparse latent representations of documents. In this article, we introduce a si…
We propose the differentially private lottery ticket mechanism (DPLTM). An end-to-end differentially private training paradigm based on the lottery ticket hypothesis. Using "high-quality winners", selected via our custom score function, DPLTM significantly improves the privacy-utility trade-off over the state-of-the-ar…
CTM improves diffusion model sampling quality with efficient ODE traversal.
New autoencoder learns structured representations without regularization.
A new method for diffusion generative models improves sample quality and speed.
Meta-Router optimizes LLM selection using gold-standard and preference-based data.
Randomized matrix compression techniques, such as the Johnson-Lindenstrauss transform, have emerged as an effective and practical way for solving large-scale problems efficiently. With a focus on computational efficiency, however, forsaking solutions quality and accuracy becomes the trade-off. In this paper, we investi…
DAISYnt evaluates synthetic data quality and privacy in regulated domains.
We propose a hybrid algorithmic strategy for complex stochastic optimization problems, which combines the use of scenario trees from multistage stochastic programming with machine learning techniques for learning a policy in the form of a statistical model, in the context of constrained vector-valued decisions. Such a …
A new approach to newsvendor problems reduces loss by up to 40%.
Given the crucial role of microtubules for cell survival, many researchers have found success using microtubule-targeting agents in the search for effective cancer therapeutics. Understanding microtubule responses to targeted interventions requires that the microtubule network within cells can be consistently observed …
We develop a unified and systematic framework for performing online nonnegative matrix factorization under a wide variety of important divergences. The online nature of our algorithm makes it particularly amenable to large-scale data. We prove that the sequence of learned dictionaries converges almost surely to the set…
Magnetic resonance image (MRI) reconstruction is a severely ill-posed linear inverse task demanding time and resource intensive computations that can substantially trade off {\it accuracy} for {\it speed} in real-time imaging. In addition, state-of-the-art compressed sensing (CS) analytics are not cognizant of the imag…
This paper improves generative models by using data scaling and theoretical analysis.
New metrics using Laplace approximation improve Gaussian process model selection.
This work improves disentanglement in latent space models without sacrificing generation quality.