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.
Enhanced Bayesian target encoding uses sampling techniques to improve model performance.
Stochastic encoders outperform deterministic ones in 'perfect perceptual quality'.
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…
New definition reveals encoding explanations that retain predictive power.
Randomized positional encodings boost transformer performance on longer sequences.
Transformer struggles with arithmetic length but improves with explicit structure encoding.
Generative adversarial networks (GANs) are capable of producing high quality image samples. However, unlike variational autoencoders (VAEs), GANs lack encoders that provide the inverse mapping for the generators, i.e., encode images back to the latent space. In this work, we consider adversarially learned generative mo…
New bounds for quantum circuits depend on how data is encoded.
MUTE improves neural network performance with efficient target encoding.
What do auto-encoders learn about the underlying data generating distribution? Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of data. This paper clarifies some of these previous observations by showing that minimizing a particular form of regularized recons…
Proposes DC3-GAN for diverse unsupervised conditional generation.
Extends graph encoder embedding to weighted graphs and matrices.
New encoding improves volatility surface generation and risk management.
Encoder-decoder GANs architectures (e.g., BiGAN and ALI) seek to add an inference mechanism to the GANs setup, consisting of a small encoder deep net that maps data-points to their succinct encodings. The intuition is that being forced to train an encoder alongside the usual generator forces the system to learn meaning…
Generative adversarial networks (GANs) have demonstrated to be successful at generating realistic real-world images. In this paper we compare various GAN techniques, both supervised and unsupervised. The effects on training stability of different objective functions are compared. We add an encoder to the network, makin…
New insights into how encoder-decoder networks generate attention matrices.
New method enforces encoder sparsity in HPF for more interpretable feature selection.
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…
Humans are able to imagine a person's voice from the person's appearance and imagine the person's appearance from his/her voice. In this paper, we make the first attempt to develop a method that can convert speech into a voice that matches an input face image and generate a face image that matches the voice of the inpu…
EncGAN learns multi-manifold structure and abstract features using an encoder.
The paper explores how invertibility affects the complexity of encoder models in VAEs.
Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversarial Networks (GANs) can learn data distributions without needing a parametric assumption on the output density. We show on a speech source se…
Encoding a sequence of observations is an essential task with many applications. The encoding can become highly efficient when the observations are generated by a dynamical system. A dynamical system imposes regularities on the observations that can be leveraged to achieve a more efficient code. We propose a method to …
Study efficient neural operator learning using variation spaces.
HyperVAE encodes distributions of distributions using variational inference.
Fisher auto-encoders use Fisher divergence for more robust generative modeling.
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…
A new method uses persistent homology to assess auto-encoders' latent manifold quality.
Paper proposes a new method for learning deep generative models using annealed importance sampling.
Graph attention auto-encoder reconstructs graph structure and attributes.
Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode collapse in the learned generative model by ensuring that it is grounded in all the ava…
Paper introduces a new method for Transformers with linear complexity.
This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and control the output words based on the estimation in the decoder. Our method shows si…
Adaptive graph auto-encoder improves general data clustering.
Develops a new non-adversarial framework for better generative models.
Diversity plays a vital role in many text generating applications. In recent years, Conditional Variational Auto Encoders (CVAE) have shown promising performances for this task. However, they often encounter the so called KL-Vanishing problem. Previous works mitigated such problem by heuristic methods such as strengthe…
In this paper, we propose an auto-encoder based generative neural network model whose encoder compresses the inputs into vectors in the tangent space of a special Lie group manifold: upper triangular positive definite affine transform matrices (UTDATs). UTDATs are representations of Gaussian distributions and can strai…
Deep learning models have shown state-of-the-art performance in many inverse reconstruction problems. However, it is not well understood what properties of the latent representation may improve the generalization ability of the network. Furthermore, limited models have been presented for inverse reconstructions over ti…
Derives formulae for general permutation equivariant layers and presents a second order graph variational encoder.
A novel generative encoder model for imaging and image processing.
Paper proposes Adversarial CCA for multi-view alignment and generation.
Transformer adapts to graphs with adaptive attention and auto-regressive decoding.
Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs) provide impressive image generations from Gaussian white noise, but the underlying mathematics are not well understood. We compute deep convolutional network generators by inverting a fixed embedding operator. Therefore, they do not require to be o…
A new triad decoder improves graph auto-encoders' performance.
DCM uses diffusion models to answer causal queries from observational data.
SIG-VAE enhances VGAE for graph data modeling.
Improves latent space structure for better data representation.
Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples () conditioned on both latent variables () and known auxiliary information (). We propose the Bidirectional cGAN (BiCoGAN), which effectively disentangles and in the generation process and provides a…