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.
Unified approach for nonparametric regression and conditional distribution learning.
New approach generates better synthetic data for neural program synthesis.
Survey compares methods for generating artificial outliers.
A new method generates meta-tasks using generative models for unsupervised learning.
New approach to symmetries in teleparallel geometries with non-trivial isotropy groups.
Saliency maps are often used in computer vision to provide intuitive interpretations of what input regions a model has used to produce a specific prediction. A number of approaches to saliency map generation are available, but most require access to model parameters. This work proposes an approach for saliency map gene…
New approach combines likelihood and adversarial losses for better precipitation predictions.
This paper proposes an EM approach to reduce inference latency in NAR sequence generation.
A new CA-GAN architecture improves minority class data generation in health datasets.
Existing approaches for automatically generating mathematical word problems are deprived of customizability and creativity due to the inherent nature of template-based mechanisms they employ. We present a solution to this problem with the use of deep neural language generation mechanisms. Our approach uses a Character …
Flow-based data sets are necessary for evaluating network-based intrusion detection systems (NIDS). In this work, we propose a novel methodology for generating realistic flow-based network traffic. Our approach is based on Generative Adversarial Networks (GANs) which achieve good results for image generation. A major c…
New approach generates optimal disturbances for controller verification.
The traditional approach of hand-crafting priors (such as sparsity) for solving inverse problems is slowly being replaced by the use of richer learned priors (such as those modeled by generative adversarial networks, or GANs). In this work, we study the algorithmic aspects of such a learning-based approach from a theor…
Generating video frames that accurately predict future world states is challenging. Existing approaches either fail to capture the full distribution of outcomes, or yield blurry generations, or both. In this paper we introduce an unsupervised video generation model that learns a prior model of uncertainty in a given en…
We propose a general framework for solving statistical mechanics of systems with finite size. The approach extends the celebrated variational mean-field approaches using autoregressive neural networks, which support direct sampling and exact calculation of normalized probability of configurations. It computes variation…
Generative models for complex stochastic dynamics using adversarial learning.
Paper develops a novel approach for optimal control using kernel methods.
Efficient exploration remains a challenging problem in reinforcement learning, especially for those tasks where rewards from environments are sparse. A commonly used approach for exploring such environments is to introduce some "intrinsic" reward. In this work, we focus on model uncertainty estimation as an intrinsic r…
Existing automatic music generation approaches that feature deep learning can be broadly classified into two types: raw audio models and symbolic models. Symbolic models, which train and generate at the note level, are currently the more prevalent approach; these models can capture long-range dependencies of melodic st…
The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and develop new models th…
As a new approach to train generative models, \emph{generative adversarial networks} (GANs) have achieved considerable success in image generation. This framework has also recently been applied to data with graph structures. We propose labeled-graph generative adversarial networks (LGGAN) to train deep generative model…
Develops a new model-free approach to portfolio theory using rough paths.
New approach improves model generalization through distributionally robust learning.
Variational inference (VI) and Markov chain Monte Carlo (MCMC) are two main approximate approaches for learning deep generative models by maximizing marginal likelihood. In this paper, we propose using annealed importance sampling for learning deep generative models. Our proposed approach bridges VI with MCMC. It gener…
This paper uses VAE to generate extreme events from multivariate data.
The vast majority of network datasets contains errors and omissions, although this is rarely incorporated in traditional network analysis. Recently, an increasing effort has been made to fill this methodological gap by developing network reconstruction approaches based on Bayesian inference. These approaches, however, …
Recent work shows GRW approaches do not improve over ERM in distributional shift.
Paper tackles BNSL with IP, improving quality of solutions.
New deep learning method validated across multiple sleep staging databases.
Proposes a method to generate text that adheres to logical constraints.
We investigate the optimization of two probabilistic generative models with binary latent variables using a novel variational EM approach. The approach distinguishes itself from previous variational approaches by using latent states as variational parameters. Here we use efficient and general purpose sampling procedure…
We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our…
Paper tackles outlier detection in signals modeled by generative models with theoretical guarantees.
Given two distinct datasets, an important question is if they have arisen from the the same data generating function or alternatively how their data generating functions diverge from one another. In this paper, we introduce an approach for measuring the distance between two datasets with high dimensionality using varia…
New approach avoids excess empirical risk in domain generalization.
A new deep model generates molecules by fragments, improving validity and uniqueness.
New method labels GAN-generated faces without stereotyping.
Graph generation with Machine Learning is an open problem with applications in various research fields. In this work, we propose to cast the generative process of a graph into a sequential one, relying on a node ordering procedure. We use this sequential process to design a novel generative model composed of two recurr…
The paper proposes a new approach to portfolio selection that maximizes diversification and return.
Generative Adversarial Networks simulate realistic market interactions.
Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial l…
Flexible Bayesian approach for generalized linear models, especially for sparse logistic regression.
New approach uses deep generative models for inventory and pricing decisions.
New approach finds solutions to games with unbounded controls.
New algorithms solve inverse problems using deep learning, converging faster than traditional methods.
Generative ML learns optimal pursuit trajectories in pursuit-evasion games.
Study systemic risk measures and capital allocation rules, showing commonalities.
Neural random fields (NRFs), referring to a class of generative models that use neural networks to implement potential functions in random fields (a.k.a. energy-based models), are not new but receive less attention with slow progress. Different from various directed graphical models such as generative adversarial netwo…