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.
Enhances autoencoders to represent transformations explicitly.
Transformation Equivariant Representations (TERs) aim to capture the intrinsic visual structures that equivary to various transformations by expanding the notion of {\em translation} equivariance underlying the success of Convolutional Neural Networks (CNNs). For this purpose, we present both deterministic AutoEncoding…
Transformer autoencoder learns musical style from performances.
Noting the importance of the latent variables in inference and learning, we propose a novel framework for autoencoders based on the homeomorphic transformation of latent variables, which could reduce the distance between vectors in the transformed space, while preserving the topological properties of the original space…
This paper explores the problem of learning transforms for image compression via autoencoders. Usually, the rate-distortion performances of image compression are tuned by varying the quantization step size. In the case of autoen-coders, this in principle would require learning one transform per rate-distortion point at…
In this paper we propose a Deep Autoencoder MIxture Clustering (DAMIC) algorithm based on a mixture of deep autoencoders where each cluster is represented by an autoencoder. A clustering network transforms the data into another space and then selects one of the clusters. Next, the autoencoder associated with this clust…
Autoencoders help transform data representations for improved learning tasks.
GT-PCA improves PCA for image and time series data.
Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult. We propose a new class of smoothing transformations based on a mixture of two overlapping distributions, and show that the proposed transformation can be used for training binary lat…
Deep autoencoder finds linear PDE coordinates for nonlinear equations.
The study explores the compressive power of Boolean threshold autoencoders, finding that seven layers are necessary but three are not.
Few-shot domain adaptation improves autoencoder performance in changing wireless channels.
Disentangled representation learning finds compact, independent and easy-to-interpret factors of the data. Learning such has been shown to require an inductive bias, which we explicitly encode in a generative model of images. Specifically, we propose a model with two latent spaces: one that represents spatial transform…
VAELLS learns latent manifold structure to improve VAE model accuracy.
SurVAE Flows combine VAEs and flows using surjective transformations.
Model learns latent dynamics of complex systems with closed transformation paths.
MoCA uses a novel autoencoder to analyze multi-modal health data.
Paper uses autoencoders for time series clustering with energy data.
UT module refines VAE latent space, improving disentanglement and interpretability.
CRATE-MAE learns structured representations from unlabeled data.
Adaptive framework predicts stock prices better during volatile periods.
Unified model trained on images and videos using masked autoencoding.
Variational autoencoder is a powerful deep generative model with variational inference. The practice of modeling latent variables in the VAE's original formulation as normal distributions with a diagonal covariance matrix limits the flexibility to match the true posterior distribution. We propose a new transformation, …
FF layers in transformers are nearly as interpretable as sparse autoencoders.
A new method generates synthetic data with realistic marginal distributions.
Improved SINDy autoencoder for identifying noisy dynamical systems.
This paper clarifies VAE's property through geometric and information-theoretic interpretations.
GE-autoencoder identifies spontaneous symmetry breaking in systems.
The autoencoder is an artificial neural network model that learns hidden representations of unlabeled data. With a linear transfer function it is similar to the principal component analysis (PCA). While both methods use weight vectors for linear transformations, the autoencoder does not come with any indication similar…
Automates galaxy morphology classification with less human labelling.
Dimension Estimation (DE) and Dimension Reduction (DR) are two closely related topics, but with quite different goals. In DE, one attempts to estimate the intrinsic dimensionality or number of latent variables in a set of measurements of a random vector. However, in DR, one attempts to project a random vector, either l…
Generates high-quality images using sparse DCT representations.
We develop a flexible framework for low-rank matrix estimation that allows us to transform noise models into regularization schemes via a simple bootstrap algorithm. Effectively, our procedure seeks an autoencoding basis for the observed matrix that is stable with respect to the specified noise model; we call the resul…
Proposes a new latent variable model for hyperspherical latent spaces.
Paper proposes a novel approach to improve temporal clustering of time series data.
Feature selection is a dimensionality reduction technique that selects a subset of representative features from high dimensional data by eliminating irrelevant and redundant features. Recently, feature selection combined with sparse learning has attracted significant attention due to its outstanding performance compare…
We introduce the vine copula autoencoder (VCAE), a flexible generative model for high-dimensional distributions built in a straightforward three-step procedure. First, an autoencoder (AE) compresses the data into a lower dimensional representation. Second, the multivariate distribution of the encoded data is estimated …
The problem of domain generalization is to take knowledge acquired from a number of related domains where training data is available, and to then successfully apply it to previously unseen domains. We propose a new feature learning algorithm, Multi-Task Autoencoder (MTAE), that provides good generalization performance …
Motion sensors such as accelerometers and gyroscopes measure the instant acceleration and rotation of a device, in three dimensions. Raw data streams from motion sensors embedded in portable and wearable devices may reveal private information about users without their awareness. For example, motion data might disclose …
The paper provides convergence guarantees for ODE-based generative models using transformers.
Theoretical analysis of vision transformers' performance with MAE and CL objectives.
The paper discovers a hidden component in data using an autoencoder with a discriminator.
Boltzmann machines are powerful distributions that have been shown to be an effective prior over binary latent variables in variational autoencoders (VAEs). However, previous methods for training discrete VAEs have used the evidence lower bound and not the tighter importance-weighted bound. We propose two approaches fo…
Variational inference methods often focus on the problem of efficient model optimization, with little emphasis on the choice of the approximating posterior. In this paper, we review and implement the various methods that enable us to develop a rich family of approximating posteriors. We show that one particular method …
A deep learning model organizes RNA graphs to reveal folding patterns and properties.
Proves identifiability of deep latent variable models without auxiliary information.
WAEs offer a statistical understanding of density estimation and error bounds.
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for learning features relevant to discriminative tasks. Autoencoders, in particular, have proven to be an effective way to learn latent codes th…