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.
InfoCNF improves conditional image generation by optimizing latent code partitioning and solver error tolerances.
A novel MCMC method clusters data faster and more accurately.
Paper analyzes latent space geometry in generative models using Fisher information.
Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) is demonstrated to efficiently solve eigenvalue problems for graph Laplacians that appear in spectral clustering. For static graph partitioning, 10-20 iterations of LOBPCG without preconditioning result in ~10x error reduction, enough to achieve 100% corr…
Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes. However, they are sometimes ambiguous as they tend to produce reconstructions that are not…
Proposes a framework to improve VAE latent codes using mutual information.
Improved upper bound for mass partitioning problem using Gray codes.
Proposes a framework to maximize mutual information in VAE models for better latent code representation.
Auto-decoder synthesizes graphs from latent codes.
A new method for image translation without paired data.
Unsupervised framework learns latent codes for controllable generation.
Deep model learns complex latent codes without assuming factor structure.
We propose moment-based variational inference as a flexible framework for approximate smoothing of latent Markov jump processes. The main ingredient of our approach is to partition the set of all transitions of the latent process into classes. This allows to express the Kullback-Leibler divergence between the approxima…
NeoMLP improves neural fields by adding self-attention for better downstream tasks.
Proposes a non-parametric method for deep discrete latent variable models.
Observed associations in a database may be due in whole or part to variations in unrecorded (latent) variables. Identifying such variables and their causal relationships with one another is a principal goal in many scientific and practical domains. Previous work shows that, given a partition of observed variables such …
Many image-to-image translation problems are ambiguous, as a single input image may correspond to multiple possible outputs. In this work, we aim to model a \emph{distribution} of possible outputs in a conditional generative modeling setting. The ambiguity of the mapping is distilled in a low-dimensional latent vector,…
New method compresses facial videos using GANs and latent space optimization.
Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding. In this paper, we propose a generative model to learn compact latent codes that can efficiently represent and reconstruct a video sequence from its missing or under-sampled measuremen…
VED framework learns low-dimensional latent representations of physical systems.
We address the problem of severe class imbalance in unsupervised domain adaptation, when the class spaces in source and target domains diverge considerably. Till recently, domain adaptation methods assumed the aligned class spaces, such that reducing distribution divergence makes the transfer between domains easier. Su…
Generalizes bits back coding for time-series models with latent Markov structures.
Paper proposes structured semantic perturbations to improve adversarial attacks.
A method to improve image synthesis diversity using mutual information.
DD-VAE uses deterministic decoding for better latent code utilization in discrete data.
We consider the problem of training generative models with deep neural networks as generators, i.e. to map latent codes to data points. Whereas the dominant paradigm combines simple priors over codes with complex deterministic models, we propose instead to use more flexible code distributions. These distributions are e…
We discuss a variant of `blind' community detection, in which we aim to partition an unobserved network from the observation of a (dynamical) graph signal defined on the network. We consider a scenario where our observed graph signals are obtained by filtering white noise input, and the underlying network is different …
A new approach predicts next observations without explicit decoding for better control.
Sparse codes improve optimal control tasks with correlated inputs.
Study shows how to manipulate VAEs for attacks and assess their robustness.
A new method learns graph compression from data.
We consider the problem of training generative models with deep neural networks as generators, i.e. to map latent codes to data points. Whereas the dominant paradigm combines simple priors over codes with complex deterministic models, we argue that it might be advantageous to use more flexible code distributions. We de…
Quantized-TinyLLaVA reduces communication costs in split learning for multimodal models.
The bits-back argument suggests that latent variable models can be turned into lossless compression schemes. Translating the bits-back argument into efficient and practical lossless compression schemes for general latent variable models, however, is still an open problem. Bits-Back with Asymmetric Numeral Systems (BB-A…
We present a novel method for hierarchical topic detection where topics are obtained by clustering documents in multiple ways. Specifically, we model document collections using a class of graphical models called hierarchical latent tree models (HLTMs). The variables at the bottom level of an HLTM are observed binary va…
Improved neural population modeling using shared features and ensemble detection.
We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data. Our model allows simultaneous inference of the number of binary latent variables, and their values. The latent variables preserve neighbourhood structure of the data in a sense that objects in the same semanti…
A novel variational autoencoder is developed to model images, as well as associated labels or captions. The Deep Generative Deconvolutional Network (DGDN) is used as a decoder of the latent image features, and a deep Convolutional Neural Network (CNN) is used as an image encoder; the CNN is used to approximate a distri…
We propose a novel neural sequence prediction method based on \textit{error-correcting output codes} that avoids exact softmax normalization and allows for a tradeoff between speed and performance. Instead of minimizing measures between the predicted probability distribution and true distribution, we use error-correcti…
Model infers latent variables in sparse coding models using Langevin dynamics.
The beta-negative binomial process (BNBP), an integer-valued stochastic process, is employed to partition a count vector into a latent random count matrix. As the marginal probability distribution of the BNBP that governs the exchangeable random partitions of grouped data has not yet been developed, current inference f…
This paper introduces Associative Compression Networks (ACNs), a new framework for variational autoencoding with neural networks. The system differs from existing variational autoencoders (VAEs) in that the prior distribution used to model each code is conditioned on a similar code from the dataset. In compression term…
New model captures patient-level EHR data efficiently.
The study analyzes how data augmentation helps isolate content from style in self-supervised learning.
A new method for disentangled latent spaces in VAEs that can manipulate attributes.
This paper addresses problematic global optima in VAEs, proposing a new inference method.
FairGP uses graph partitioning to make Graph Transformers fair and scalable.
Bayesian approach for multifile record linkage and duplicate detection.