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.
New method controls posterior collapse in VAEs without network architecture constraints.
3BASiL-TM decomposes LLMs into sparse and low-rank matrices for efficient compression.
Enhances interpretability of linear latent spaces through automated clustering and ranking.
The paper analyzes a private likelihood-ratio test for frequency tables under differential privacy constraints.
Label smoothing improves model robustness against misspecification.
GCVAE improves disentanglement in VAEs while balancing reconstruction error.
We propose a novel autoencoding model called Pairwise Augmented GANs. We train a generator and an encoder jointly and in an adversarial manner. The generator network learns to sample realistic objects. In turn, the encoder network at the same time is trained to map the true data distribution to the prior in latent spac…
As deep Variational Auto-Encoder (VAE) frameworks become more widely used for modeling biomolecular simulation data, we emphasize the capability of the VAE architecture to concurrently maximize the timescale of the latent space while inferring a reduced coordinate, which assists in finding slow processes as according t…
Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled to the high resolution (HR) space using a single filter, commonly…
Adaptive LR improves neural network Lipschitz regularity without slowing convergence.
We propose a novel approach for preserving topological structures of the input space in latent representations of autoencoders. Using persistent homology, a technique from topological data analysis, we calculate topological signatures of both the input and latent space to derive a topological loss term. Under weak theo…
Proposes AEGAN for stable GAN training.
SentenceMIM learns rich latent representations for variable-length language data.
We find optimal learning rate schedules for a random feature model.
Boosts neural network performance by improving weight separability.
VAE struggles with distribution class sharpness, which can be learned dynamically.
Paper finds sharpness differences in transformer blocks accelerating LLM training.
Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs). Even for the baseline of a constant learning rate, it is non-trivial to choose a good constant value for training a DNN. Dynamic learning rates involve multi-step tuning of LR values at various stages of th…
VED framework learns low-dimensional latent representations of physical systems.
An LR-structure on a Lie algebra is a bilinear product, satisfying certain commutativity relations, and which is compatible with the Lie product. LR-structures arise in the study of simply transitive affine actions on Lie groups. In particular one is interested in the question which Lie algebras admit a complete LR-str…
New method for valid prediction sets in high-dimensional covariate shifts.
A new method improves molecule generation accuracy and efficiency.
We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound. We provide conditions under which they recover the data distribution and learn latent features, and formally show that common issues such as blurry samples and uninformative latent feat…
Novel method learns time series dynamics without reconstruction.
State of the art deep generative networks are capable of producing images with such incredible realism that they can be suspected of memorizing training images. It is why it is not uncommon to include visualizations of training set nearest neighbors, to suggest generated images are not simply memorized. We demonstrate …
Improved model-free RL from images with stable training.
As advances in signature recognition have reached a new plateau of performance at around 2% error rate, it is interesting to investigate alternative approaches. The approach detailed in this paper looks at using Variational Auto-Encoders (VAEs) to learn a latent space representation of genuine signatures. This is then …
EnVAE uses energy score for likelihood-free VAEs, improving image reconstructions.
The variational autoencoder (VAE) framework is a popular option for training unsupervised generative models, featuring ease of training and latent representation of data. The objective function of VAE does not guarantee to achieve the latter, however, and failure to do so leads to a frequent failure mode called posteri…
DCAE learns compact latent representations for one-class novelty detection.
New method reconstructs hidden dynamics from low-dimensional time series.
Large learning rates lead to optimal generalization if chosen carefully.
We review the notion of a linearity-generating (LG) process introduced by Gabaix (2007) and relate LG processes to linear-rational (LR) models studied by Filipovic, Larsson, and Trolle (2017). We show that every LR model can be represented as an LG process and vice versa. We find that LR models have two basic propertie…
MLR-SNet learns flexible LR schedules for diverse tasks.
Proposes a conservative LR estimator for infrequent data near a frequency threshold.
ADEC addresses feature randomness and drift in autoencoder-based clustering.
Domain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may cause the loss of many important properties across both domains. In this manuscri…
LMMVAE improves VAE for correlated data by separating latent variables into fixed and random parts.
A trade-off exists between reconstruction quality and the prior regularisation in the Evidence Lower Bound (ELBO) loss that Variational Autoencoder (VAE) models use for learning. There are few satisfactory approaches to deal with a balance between the prior and reconstruction objective, with most methods dealing with t…
We employ unsupervised machine learning techniques to learn latent parameters which best describe states of the two-dimensional Ising model and the three-dimensional XY model. These methods range from principal component analysis to artificial neural network based variational autoencoders. The states are sampled using …
Paper simulates LR fuzzy intervals with interval-valued cores.
This work uses action equivariance to learn structured latent spaces for reinforcement learning.
We solve a high-dimensional model where nonlinear autoencoders detect hidden structure missed by PCA.
Study reconstructs causal graph from latent variables using mixture oracles.
There is an increasingly apparent need for validating the classifications made by deep learning systems in safety-critical applications like autonomous vehicle systems. A number of recent papers have proposed methods for detecting anomalous image data that appear different from known inlier data samples, including reco…
Proposes a new method for efficient model reconstruction with uncertain parameters.
In this work, a deep learning-based method for log-likelihood ratio (LLR) lossy compression and quantization is proposed, with emphasis on a single-input single-output uncorrelated fading communication setting. A deep autoencoder network is trained to compress, quantize and reconstruct the bit log-likelihood ratios cor…
In recent years Variation Autoencoders have become one of the most popular unsupervised learning of complicated distributions.Variational Autoencoder (VAE) provides more efficient reconstructive performance over a traditional autoencoder. Variational auto enocders make better approximaiton than MCMC. The VAE defines a …