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.
Randomized positional encodings boost transformer performance on longer sequences.
For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework. VHE…
We study the role of latent space dimensionality in Wasserstein auto-encoders (WAEs). Through experimentation on synthetic and real datasets, we argue that random encoders should be preferred over deterministic encoders. We highlight the potential of WAEs for representation learning with promising results on a benchmar…
Sparse neural encoding can store more memories as targets become sparser.
A fast graph embedding method for large graphs.
Paper explores embedding methods for detecting pseudo-cliques in random graphs, showing limitations and potential.
CMRFs extend PGMs for topological data, capturing both conditional and marginal dependencies.
MCSAE improves speaker embedding by focusing on both high- and low-level features.
This paper explores GNN functions on random graphs, highlighting the importance of node Positional Encodings.
Capturing sentence semantics plays a vital role in a range of text mining applications. Despite continuous efforts on the development of related datasets and models in the general domain, both datasets and models are limited in biomedical and clinical domains. The BioCreative/OHNLP organizers have made the first attemp…
Information bottleneck (IB) is a technique for extracting information in one random variable that is relevant for predicting another random variable . IB works by encoding in a compressed "bottleneck" random variable from which can be accurately decoded. However, finding the optimal bottleneck variab…
Privacy-preserving eye tracking framework using synthetic images.
Random hyperbolic surfaces with punctures converge to the Brownian sphere.
In this note we present a generative model of natural images consisting of a deep hierarchy of layers of latent random variables, each of which follows a new type of distribution that we call rectified Gaussian. These rectified Gaussian units allow spike-and-slab type sparsity, while retaining the differentiability nec…
For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. "Dirty" non-curated data gives rise to categorical variables with a very high cardinality but redundancy: several categories reflect the same ent…
The paper verifies the robustness of classifier ensembles against randomized attacks.
Exact optimality achieved in distributed mean estimation with shared randomness.
CIPNN model tackles continuous latent variables, solving intractable posterior problems.
We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, bu…
Regularized target encoding beats traditional methods for high cardinality features in ML.
Integrates neural encoders into GLMMs for multimodal data analysis.
A simple encoder and complex decoder for secure image encryption and decryption.
Novel PCA method for high-dimensional inverse problems.
In (\cite{zhang2014nonlinear,zhang2014nonlinear2}), we have viewed machine learning as a coding and dimensionality reduction problem, and further proposed a simple unsupervised dimensionality reduction method, entitled deep distributed random samplings (DDRS). In this paper, we further extend it to supervised learning …
Quantum-assisted Gaussian process speeds up data regression.
In this paper, we present a novel approach for initializing deep neural networks, i.e., by turning PCA into neural layers. Usually, the initialization of the weights of a deep neural network is done in one of the three following ways: 1) with random values, 2) layer-wise, usually as Deep Belief Network or as auto-encod…
This paper considers the problem of implementing large-scale gradient descent algorithms in a distributed computing setting in the presence of {\em straggling} processors. To mitigate the effect of the stragglers, it has been previously proposed to encode the data with an erasure-correcting code and decode at the maste…
Node embeddings have become an ubiquitous technique for representing graph data in a low dimensional space. Graph autoencoders, as one of the widely adapted deep models, have been proposed to learn graph embeddings in an unsupervised way by minimizing the reconstruction error for the graph data. However, its reconstruc…
Paper explores neural network approximations on sphere domains.
Generative Adversarial Networks (GANs) play an increasingly important role in machine learning. However, there is one fundamental issue hindering their practical applications: the absence of capability for encoding real-world samples. The conventional way of addressing this issue is to learn an encoder for GAN via Vari…
Paper proposes Adversarial CCA for multi-view alignment and generation.
The large memory requirements of deep neural networks limit their deployment and adoption on many devices. Model compression methods effectively reduce the memory requirements of these models, usually through applying transformations such as weight pruning or quantization. In this paper, we present a novel scheme for l…
We introduce a novel encoder-decoder architecture to embed functional processes into latent vector spaces. This embedding can then be decoded to sample the encoded functions over any arbitrary domain. This autoencoder generalizes the recently introduced Conditional Neural Process (CNP) model of random processes. Our ar…
Study on neural networks with non-normal interactions reveals unique spectral properties.
Principal component analysis, dictionary learning, and auto-encoders are all unsupervised methods for learning representations from a large amount of training data. In all these methods, the higher the dimensions of the input data, the longer it takes to learn. We introduce a class of neural networks, termed RandNet, f…
For the pedestrian observer, financial markets look completely random with erratic and uncontrollable behavior. To a large extend, this is correct. At first approximation the difference between real price changes and the random walk model is too small to be detected using traditional time series analysis. However, we s…
SUMO provides unbiased log marginal likelihood estimation for latent variable models.
Paper develops a decoder for sparse codes without encoder matrix, achieving optimal recovery.
Model place cells as spatial embeddings for efficient path planning and cognitive map construction.
Generative AutoEncoders require a chosen probability distribution in latent space, usually multivariate Gaussian. The original Variational AutoEncoder (VAE) uses randomness in encoder - causing problematic distortion, and overlaps in latent space for distinct inputs. It turned out unnecessary: we can instead use determ…
Paper proposes a novel auto-encoder for latent density estimation.
BEGIN network models binary data without parametric assumptions.
Free Random Projection enhances reinforcement learning by naturally incorporating hierarchical structure.
Quantum machine learning tackles large datasets with randomized measurements.
The paper describes fitting submanifolds to data using Sussmann's orbit theorem.
The paper introduces a method for detecting principal communities and embedding vertices.
A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to optimize performance on training data when the real objective is to generalize well to unseen data. Although there is enough numerical eviden…
For the pedestrian observer, financial markets look completely random with erratic and uncontrollable behavior. To a large extend, this is correct. At first approximation the difference between real price changes and the random walk model is too small to be detected using traditional time series analysis. However, we s…