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.
Improved unlearning in LLMs using contrastive decoding.
Adaptive contrastive search improves text generation quality and diversity.
Decoding strategies often exclude human-like tokens, creating a detectable gap in generated text.
A decoder helps interpret neural network layers.
The paper develops a theory for speculative decoding acceptance criteria.
We introduce the Mutual Information Machine (MIM), a probabilistic auto-encoder for learning joint distributions over observations and latent variables. MIM reflects three design principles: 1) low divergence, to encourage the encoder and decoder to learn consistent factorizations of the same underlying distribution; 2…
SLED improves factuality in LLMs without external knowledge.
Third-generation neural networks, or Spiking Neural Networks (SNNs), aim at harnessing the energy efficiency of spike-domain processing by building on computing elements that operate on, and exchange, spikes. In this paper, the problem of training a two-layer SNN is studied for the purpose of classification, under a Ge…
VCL adds uncertainty to contrastive learning models.
We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly designed decoder which builds a completely symmetric autoencoder form. For the re…
This paper uses diffusion models for lossy image compression, improving perceptual metrics and practicality.
A new framework learns differentiable structured losses from data.
Self-supervised method improves biosignal models with limited labeled data and subjects.
Deep generative models have been praised for their ability to learn smooth latent representation of images, text, and audio, which can then be used to generate new, plausible data. However, current generative models are unable to work with molecular graphs due to their unique characteristics-their underlying structure …
We take steps towards understanding the "posterior collapse (PC)" difficulty in variational autoencoders (VAEs),~i.e. a degenerate optimum in which the latent codes become independent of their corresponding inputs. We rely on calculus of variations and theoretically explore a few popular VAE models, showing that PC alw…
Locally private online quantile regression method addresses privacy constraints.
cMIM improves representation learning without positive-pair augmentations.
Improved VAEs by training a contrastive prior to match posterior.
LoCo learns local representations without end-to-end synchronization, improving performance on complex tasks.
Improved unsupervised probing for ranking tasks using Contrast-Consistent Ranking.
New Dreamer model tackles object vanishing in robot learning.
This paper describes a novel energy-based probabilistic distribution that represents complex-valued data and explains how to apply it to direct feature extraction from complex-valued spectra. The proposed model, the complex-valued restricted Boltzmann machine (CRBM), is designed to deal with complex-valued visible unit…
CMDNet simplifies MAP detection for large systems with probabilistic relaxation.
A new loss function ED simplifies training energy-based models without scores.
We are motivated by problems that arise in a number of applications such as Online Marketing and Explosives detection, where the observations are usually modeled using Poisson statistics. We model each observation as a Poisson random variable whose mean is a sparse linear superposition of known patterns. Unlike many co…
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…
As a technology to read brain states from measurable brain activities, brain decoding are widely applied in industries and medical sciences. In spite of high demands in these applications for a universal decoder that can be applied to all individuals simultaneously, large variation in brain activities across individual…
Novel low-rank neural decoder improves -ECoG neural decoding.
The paper introduces FMCI and hybrid decoding for hidden Markov models.
This paper introduces a cross adversarial source separation (CASS) framework via autoencoder, a new model that aims at separating an input signal consisting of a mixture of multiple components into individual components defined via adversarial learning and autoencoder fitting. CASS unifies popular generative networks l…
OLinear forecasts time series more efficiently by transforming data orthogonally.
Study examines how decoding algorithms affect fairness in language generation models.
We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophisticated decoders that increase the complexity of training and evaluat…
In this paper, we use reinforcement learning to find effective decoding strategies for binary linear codes. We start by reviewing several iterative decoding algorithms that involve a decision-making process at each step, including bit-flipping (BF) decoding, residual belief propagation, and anchor decoding. We then ill…
This paper analyzes speculative decoding, a method to speed up large language model inferences.
Finding optimal correction of errors in generic stabilizer codes is a computationally hard problem, even for simple noise models. While this task can be simplified for codes with some structure, such as topological stabilizer codes, developing good and efficient decoders still remains a challenge. In our work, we syste…
Improving the interpretability of brain decoding approaches is of primary interest in many neuroimaging studies. Despite extensive studies of this type, at present, there is no formal definition for interpretability of brain decoding models. As a consequence, there is no quantitative measure for evaluating the interpre…
NeRF-VAE generates 3D scenes with geometric structure from few images.
Recent developments in the field of deep learning have motivated many researchers to apply these methods to problems in quantum information. Torlai and Melko first proposed a decoder for surface codes based on neural networks. Since then, many other researchers have applied neural networks to study a variety of problem…
HAMD optimizes cubic portfolios without quadratization, achieving better results.
LIMP learns latent shapes with metric preservation, improving generative models.
CARDS improves decoding efficiency and alignment quality for LLMs.
Inspired by recent advances in deep learning, we propose a novel iterative BP-CNN architecture for channel decoding under correlated noise. This architecture concatenates a trained convolutional neural network (CNN) with a standard belief-propagation (BP) decoder. The standard BP decoder is used to estimate the coded b…
This work proposes an efficient autoregressive model for text generation.
Proposes a secure communication method independent of eavesdropper's decoder.
Finding efficient decoders for quantum error correcting codes adapted to realistic experimental noise in fault-tolerant devices represents a significant challenge. In this paper we introduce several decoding algorithms complemented by deep neural decoders and apply them to analyze several fault-tolerant error correctio…
DD-VAE uses deterministic decoding for better latent code utilization in discrete data.
Inspired by the recent advances in deep learning (DL), this work presents a deep neural network aided decoding algorithm for binary linear codes. Based on the concept of deep unfolding, we design a decoding network by unfolding the alternating direction method of multipliers (ADMM)-penalized decoder. In addition, we pr…