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.
Paper proposes LCP for structural encodings, outperforming existing methods.
Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data, several graph auto-encoders have recently been proposed, but they neglect to reco…
GraphToken encodes structured data for LLMs, improving graph reasoning tasks.
Learning an encoding of feature vectors in terms of an over-complete dictionary or a information geometric (Fisher vectors) construct is wide-spread in statistical signal processing and computer vision. In content based information retrieval using deep-learning classifiers, such encodings are learnt on the flattened la…
Transformer struggles with arithmetic length but improves with explicit structure encoding.
ETC improves Transformer models for long and structured inputs.
New insights into encoder-decoder structures using information measures.
In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders …
A model learns stock trading rules from raw prices using encoder-decoder neural network.
Improves latent space structure for better data representation.
Binary encoding enables neural networks to extrapolate periodic functions.
New method discovers causal structures from incomplete data.
The (variational) graph auto-encoder and its variants have been popularly used for representation learning on graph-structured data. While the encoder is often a powerful graph convolutional network, the decoder reconstructs the graph structure by only considering two nodes at a time, thus ignoring possible interaction…
GTA improves transformer-based NVS models by encoding geometric structure.
We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs. We demonstrate this model us…
Paper encodes textile structures and classifies them up to complexity five.
Directly compute classification by learning features with class scores.
We present an encoder-powered generative adversarial network (EncGAN) that is able to learn both the multi-manifold structure and the abstract features of data. Unlike the conventional decoder-based GANs, EncGAN uses an encoder to model the manifold structure and invert the encoder to generate data. This unique scheme …
We propose the Wasserstein Auto-Encoder (WAE)---a new algorithm for building a generative model of the data distribution. WAE minimizes a penalized form of the Wasserstein distance between the model distribution and the target distribution, which leads to a different regularizer than the one used by the Variational Aut…
Paper proposes a new Autoencoder for robustly encoding white matter streamlines.
In "extreme" computational imaging that collects extremely undersampled or noisy measurements, obtaining an accurate image within a reasonable computing time is challenging. Incorporating image mapping convolutional neural networks (CNN) into iterative image recovery has great potential to resolve this issue. This pape…
Defines special Joyce structures for ASK manifolds encoding real HK structures.
New bounds for quantum circuits depend on how data is encoded.
The paper explores how AI systems use information geometry to encode semantic structure.
The paper uses neural networks to forecast time series data.
Study efficient neural operator learning using variation spaces.
A new drug embedding method using hierarchical drug relations and chemical structures.
Learning the Markov network structure from data is a problem that has received considerable attention in machine learning, and in many other application fields. This work focuses on a particular approach for this purpose called independence-based learning. Such approach guarantees the learning of the correct structure …
Improved VAE models avoid posterior collapse in text modeling.
Graph-to-Tree Neural Networks improve structured input-output translation in tasks like semantic parsing and math word problems.
Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-dimensional latent representations of high-dimensional data. When the correlation structure among data points is available, previous work proposed Correlated Variational Auto-Encoders (CVAEs), which employ a structured mixture model as …
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…
Graph auto-encoders predict stock market instability by measuring graph structure changes.
Unified framework analyzes and compares RFF and RoPE PEs for music generation.
Paper introduces Laplace-HDC for better binary hyperdimensional computing.
We consider sphere bundles P and P' of totally null planes of maximal dimension and opposite self-duality over a 4-dimensional manifold equipped with a Weyl or Riemannian geometry. The fibre product PP' of P and P' is found to be appropriate for the encoding of both the selfdual and the Einstein-Weyl equations for the …
Graph structured data are abundant in the real world. Among different graph types, directed acyclic graphs (DAGs) are of particular interest to machine learning researchers, as many machine learning models are realized as computations on DAGs, including neural networks and Bayesian networks. In this paper, we study dee…
Study infers tree topology from customer data using contrastive learning.
Half-AVAE enhances VAE for underdetermined ICA with adversarial training.
Transformer adapts to graphs with adaptive attention and auto-regressive decoding.
This paper explores a new framework for lossy image encryption and decryption using a simple shallow encoder neural network E for encryption, and a complex deep decoder neural network D for decryption. E is kept simple so that encoding can be done on low power and portable devices and can in principle be any nonlinear …
Transformer learns graph structure better with subgraph info.
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…
New encoding improves volatility surface generation and risk management.
The variational auto-encoder (VAE) is a popular method for learning a generative model and embeddings of the data. Many real datasets are hierarchically structured. However, traditional VAEs map data in a Euclidean latent space which cannot efficiently embed tree-like structures. Hyperbolic spaces with negative curvatu…
Single auto-encoder learns cross-domain image translation.
We introduce the Contextual Graph Markov Model, an approach combining ideas from generative models and neural networks for the processing of graph data. It founds on a constructive methodology to build a deep architecture comprising layers of probabilistic models that learn to encode the structured information in an in…
DGA and DVGA learn disentangled graph representations to improve graph analysis.