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.
GLAD improves latent graph generation by quantizing discrete latent space.
Quantizes latent space to improve disentanglement in models.
A new method for multiclass calibration using vector quantization.
Autoencoders and their variations provide unsupervised models for learning low-dimensional representations for downstream tasks. Without proper regularization, autoencoder models are susceptible to the overfitting problem and the so-called posterior collapse phenomenon. In this paper, we introduce a quantization-based …
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…
For a robot to perform complex manipulation tasks, it is necessary for it to have a good grasping ability. However, vision based robotic grasp detection is hindered by the unavailability of sufficient labelled data. Furthermore, the application of semi-supervised learning techniques to grasp detection is under-explored…
Improved vector quantization using Gaussian mixtures for better codebook utilization.
PRISM-VQ combines financial priors with vector quantization for better stock prediction.
Optimal quantization improves dataset distillation for faster training.
Paper proposes a new Autoencoder for robustly encoding white matter streamlines.
Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods. State-of-the-art techniques learn parameters of quantizers on training data for optimal performance, thus adapting quantizers to the data. In this work, we propose to reverse this paradigm and adapt the data to the quant…
Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech. Such models typically incorporate a fine-grained variational autoencoder (VAE) structure, extracting latent features at each input token (e.g., phonemes). However, generating samples …
High-risk domains require reliable confidence estimates from predictive models. Deep latent variable models provide these, but suffer from the rigid variational distributions used for tractable inference, which err on the side of overconfidence. We propose Stochastic Quantized Activation Distributions (SQUAD), which im…
Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates. Encouraged by recent success in learning discrete representations with Vector Quantized Variational Autoencoders (VQ-VAEs), we motivate the us…
A new method learns discrete representations for images and videos, improving upon previous models.
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…
Improved training for VQ-VAE models with robust codebook learning.
NM-VQTSG improves synthetic time series fidelity by aligning distributions.
QTD integrates quantization with diffusion for efficient data generation.
We propose a new Quantization algorithm for the approximation of inhomogeneous random walks, which are the key terms for the valuation of CDO-tranches in latent factor models. This approach is based on a dual quantization operator which posses an intrinsic stationarity and therefore automatically leads to a second orde…
SOM-VQ tokenizes discrete models with semantic structure and navigable topology.
Quantization-aware training can recover accuracy lost by post-training quantization.
We propose a novel algorithm for quantizing continuous latent representations in trained models. Our approach applies to deep probabilistic models, such as variational autoencoders (VAEs), and enables both data and model compression. Unlike current end-to-end neural compression methods that cater the model to a fixed q…
A new model trains prior and encoder/decoder networks simultaneously for efficient generation.
The article defines and compares two types of quantizations on compact manifolds.
A new method for unsupervised disentanglement using axis-aligned cliffs.
Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks. There has been a surge in interest in discrete latent variable models, however, despite several recent improvements, the training of discrete latent variable m…
Improved neural image compression with refined latent representations.
New method for quantizing symplectic manifolds with Lagrangian bundles.
This work analyzes VQ-VAEs using information theory, focusing on latent variables and their impact on generalization and data generation.
Neural codec for high-fidelity audio compression.
Quantizes geodesics in Kähler and Sasaki geometry.
Extends geometric quantization to singular spaces.
Analyzes quantization of flux observables in gauge theories.
The paper classifies quantizable functions and explores symmetry in quantization methods.
This paper proposes a new way to quantize classical mechanical systems. Here we use ALAG - programme to construct moduli space of half weighted Bohr - Sommerfeld lagrangian cycles of fixed volume which is our quantum phase space. "Dynamical correspondence" principle makes possible to prove that this ALAG - quantization…
New method for flux quantization on phase space stacks.
We study two quantization schemes for compact symplectic manifolds with almost complex structures. The first of these is the Spin-c quantization. We prove the analog of Kodaira vanishing for the Spin-c Dirac operator, which shows that the index space of this operator provides an honest (not virtual) vector space semicl…
Estimates means in metric spaces using quantization.
Quantizes geodesic lengths in Teichmüller spaces using algebraic methods.
We apply the geometric quantization method with real polarizations to the quantization of a symplectic torus. By quantizing with half-densities we canonically associate to the symplectic torus a projective Hilbert space and prove that the projective factor is expressible in terms of the Maslov-Kashiwara index. As in th…
Quantizes symplectic manifolds with bounded geometry using Berezin-Toeplitz method.
By the quantization condition compact quantizable Kaehler manifolds can be embedded into projective space. In this way they become projective varieties. The quantum Hilbert space of the Berezin-Toeplitz quantization (and of the geometric quantization) is the projective coordinate ring of the embedded manifold. This all…
A unified approach to geometric, symbol and deformation quantizations on a generalized flag manifold endowed with an invariant pseudo-Kaehler structure is proposed. The Hilbert space of states is realized via the Bott-Borel-Weil theorem in the sheaf cohomology of the geometric quantization line bundle. The correspondin…
We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large scale image generation. To this end, we scale and enhance the autoregressive priors used in VQ-VAE to generate synthetic samples of much higher coherence and fidelity than possible before. We use simple feed-forward encoder and dec…
TimeVQVAE uses VQ for better time series generation.
In the first part of the paper we describe the complex geometry of the universal Teichmüller space , which may be realized as an open subset in the complex Banach space of holomorphic quadratic differentials in the unit disc. The quotient of the diffeomorphism group of the circle modulo Möbius …
This work is a contribution to the area of Strict Quantization (in the sense of Rieffel) in the presence of curvature and non-Abelian group actions. More precisely, we use geometry to obtain explicit oscillatory integral formulae for strongly invariant strict deformation quantizations of a class of solvable symplectic …