Research
On-device research index

arXiv research

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.

168,742 papers · 148 categories

Trend · papers per month

22446688 · Jun 202019922001200920172026
48 results for deterministic decoding

Batch normalization with regularization turns deterministic autoencoders into generative models.

problem Creating generative models from deterministic autoencoders.
method Using batch normalization as a source of non-determinism and adding entropic regularization.
result Deterministic autoencoders can be transformed into generative models with similar performance to variational autoencoders.

The paper develops a theory for speculative decoding acceptance criteria.

problem Speculative decoding's acceptance criteria and their rejection regions.
method Characterization of rejection regions as lower level sets of the target distribution, derivation of exact and margin-based certificates.
result Relaxed and tree-based acceptance criteria substantially enlarge the region of certified acceptance.

Improved VAE models avoid posterior collapse in text modeling.

problem Posterior collapse in VAEs leads to poor data manifold parameterization.
method Coupled-VAE couples a VAE with a deterministic autoencoder to improve encoder and decoder parameterizations.
result Coupled-VAE consistently improves results in probability estimation and latent space richness.

Study reveals the regularization effect of variational distributions in VAEs.

problem Understanding the regularization role of variational distributions in VAEs.
method Analyzed the role of variational family in VAEs and studied the regularization effect on local geometry.
result Uncovered the implicit regularizer in the ββ-VAE objective and proposed a deterministic autoencoding objective.

This paper uses diffusion models for lossy image compression, improving perceptual metrics and practicality.

problem Lossy image compression with improved perceptual metrics and practicality.
method End-to-end optimized lossy image compression using conditional diffusion models.
result The model yields stronger FID scores and competitive performance in distortion metrics.

Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this work, we propose an alternative framework for generative modeling that is simpler…

2019-03-29abs ↗pdf ↗

EnVAE uses energy score for likelihood-free VAEs, improving image reconstructions.

problem Likelihood misspecification in VAEs leads to blurry reconstructions and poor data fidelity.
method Deterministic decoder, energy score as reconstruction loss, fast variant for efficiency.
result EnVAE achieves superior reconstruction and generation quality compared to likelihood-based baselines.

A new method for conditional sampling using paired Wasserstein Autoencoders.

problem Conditional sampling from complex data distributions.
method Derive a novel loss function for Wasserstein Autoencoders to enable sampling from OT-type couplings.
result Learned cost-optimal transport maps and conditional sampling from an OT-type coupling.

LLMs produce volatile sentence-level sentiment classifications that affect financial decision-making.

problem Volatile outputs from LLMs impact financial text understanding tasks.
method Case study on US equity market investing via news sentiment analysis.
result Volatile LLM outputs lead to significant variations in portfolio construction and returns.

New method ensures consistent inference across different tensor parallel sizes for large language models.

problem Non-deterministic inference in large language models due to inconsistent reduction orders across GPUs.
method Tree-Based Invariant Kernels (TBIK) that align intra- and inter-GPU reduction orders through a unified hierarchical binary tree structure.
result Bit-wise identical results across different tensor parallel sizes for RL training.

Linear recurrent networks explain reinforcement learning performance in partially observable settings.

problem Understanding why linear recurrent networks work in reinforcement learning with partial observability.
method Constructed and studied two linear filters for HMMs and action-controlled HMMs.
result Linear filters serve as sufficient statistics and reduce state ambiguity, explaining empirical reinforcement learning success.

VAEs improve representation learning by inverting the data-generating process through self-consistency.

problem VAEs struggle to invert the data-generating process, yet often succeed in representation learning.
method Studied VAEs in the limit of near-deterministic decoders, proving self-consistency and showing ELBO convergence to a regularized log-likelihood.
result VAEs can perform independent mechanism analysis (IMA), recovering true latent factors under specific conditions.

A widely studied non-deterministic polynomial time (NP) hard problem lies in finding a route between the two nodes of a graph. Often meta-heuristics algorithms such as AA^{*} are employed on graphs with a large number of nodes. Here, we propose a deep recurrent neural network architecture based on the Sequence-2-Seque…

2017-10-11abs ↗pdf ↗

The process of translation is ambiguous, in that there are typically many valid trans- lations for a given sentence. This gives rise to significant variation in parallel cor- pora, however, most current models of machine translation do not account for this variation, instead treating the prob- lem as a deterministic pr…

2018-05-28abs ↗pdf ↗

The standard approach to compressive sampling considers recovering an unknown deterministic signal with certain known structure, and designing the sub-sampling pattern and recovery algorithm based on the known structure. This approach requires looking for a good representation that reveals the signal structure, and sol…

2016-02-01abs ↗pdf ↗

Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems. Deep autoregressive models suffer from error propagation which becomes catastrophic for imputing long-range sequences. In this paper, we take a non-autoregressive approach and propose …

2019-01-30abs ↗pdf ↗

Study on theoretical limits of 0\ell_0 sparse-regression algorithms using Fl RDT.

problem Understanding the performance limits of 0\ell_0 norm based optimization algorithms in compressed sensing and sparse regression.
method Utilized Fully lifted random duality theory (Fl RDT) to analyze the maximum-likelihood (ML) decoding performance.
result Uncovered phase-transition (PT) and descending 0\ell_0 (d0\ell_0) curves that separate successful and unsuccessful algorithm performance.

Study examines how decoding algorithms affect fairness in language generation models.

problem Impact of decoding algorithms on fairness in open-ended language generation.
method Systematic analysis of top-pp, top-kk, and temperature decoding algorithms.
result Decoding algorithms significantly impact fairness across demographic groups.

Human motion prediction is a stochastic process: Given an observed sequence of poses, multiple future motions are plausible. Existing approaches to modeling this stochasticity typically combine a random noise vector with information about the previous poses. This combination, however, is done in a deterministic manner,…

2019-08-02abs ↗pdf ↗

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…

2019-04-18abs ↗pdf ↗

This paper analyzes speculative decoding, a method to speed up large language model inferences.

problem Theoretical understanding of speculative decoding is lacking.
method Conceptualizes speculative decoding as a markov chain problem and studies its key properties.
result Reveals fundamental connections between LLM components and their impact on decoding efficiency.

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…

2018-02-23abs ↗pdf ↗

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…

2016-06-17abs ↗pdf ↗

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…

2017-07-18abs ↗pdf ↗

This work proposes an efficient autoregressive model for text generation.

problem The challenge of generating high-quality text with autoregressive models.
method Introduces a cascaded decoding approach using Markov transformers to achieve sub-linear parallel time generation.
result Shows competitive accuracy/speed tradeoff compared to existing methods on five machine translation datasets.

LVM-GP solves PDEs with uncertainty using latent variables and Gaussian processes.

problem Uncertainty quantification in PDE solutions with noisy data.
method Combines latent variable model and Gaussian process for uncertainty-aware prediction.
result Efficiently captures functional dependencies and robust uncertainty quantification.

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…

2018-02-18abs ↗pdf ↗

New method aligns brain data across individuals for better brain decoding.

problem Inter-individual variability in brain response patterns limits decoder generalization.
method SpectralOT method that embeds cortical geometry into Laplace-Beltrami eigenmodes.
result SpectralOT strikes balance between aligning functional features and preserving anatomical structure.