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.

169,051 papers · 148 categories

Trend · papers per month

231463694925 · Jun 202019922001200920182026
48 results for consistency training

This paper establishes a theoretical foundation for consistency training in diffusion models.

problem Lack of a comprehensive theoretical understanding of consistency training in diffusion models.
method Demonstrates the necessity of a number of steps in consistency learning exceeding d5/2/εd^{5/2}/\varepsilon for generating samples within ε\varepsilon proximity to the target distribution.
result Establishes rigorous insights into the validity and efficacy of consistency models, offering theoretical underpinnings for their utility.

ADCMs adaptively discretize CMs for efficient training.

problem Manual discretization schemes cause repeated adjustments for different noise schedules and datasets.
method Unified framework with optimization problem, local and global consistency constraints, and Gauss-Newton method.
result Significantly improve training efficiency and generative performance of CMs.

Chronologically consistent models maintain accuracy with time-restricted data.

problem Training data introduces lookahead bias and training leakage in large language models.
method ChronoBERT and ChronoGPT trained with only available data at each time point.
result Models achieve strong performance and competitive with larger models, mitigating lookahead bias.

ICT improves semi-supervised learning by making predictions consistent at data interpolations.

problem Improving semi-supervised learning performance with limited labeled data.
method ICT encourages consistent predictions at data interpolations, reducing overfitting.
result ICT achieves state-of-the-art performance on CIFAR-10 and SVHN datasets.

Improved continuous-time consistency models for large-scale image generation.

problem Training instability and discretization errors in existing diffusion models.
method Unified theoretical framework, improved diffusion process, and network architecture.
result Trained continuous-time CMs at 1.5B parameters, achieving state-of-the-art FID scores.

Proposes a new method for rank-consistent ordinal regression without weight-sharing constraints.

problem Ordinal response variables in real-world prediction problems are often ignored by conventional classification losses.
method CORN framework using conditional training sets and the chain rule for conditional probability distributions.
result Improves performance substantially compared to the CORAL reference approach without weight-sharing restrictions.

Efficiently creates label-consistent backdoor attacks without obvious mislabeling.

problem Vulnerability of deep neural networks to backdoor attacks that can be triggered by a backdoor trigger.
method Uses adversarial perturbations and generative models to inject inputs that are consistent with their labels.
result Demonstrates the feasibility of creating undetectable backdoor attacks by maintaining label-consistency.

Improved TTS style transfer across disjoint datasets with adversarial cycle consistency.

problem Suboptimal TTS style transfer on disjoint datasets with underrepresented styles.
method Adversarial cycle consistency training with paired and unpaired triplets.
result 78% improvement in style transfer with minimal reduction in fidelity and naturalness.

Paper introduces elastic consistency for distributed SGD, enabling convergence analysis.

problem Training large-scale machine learning models in distributed environments.
method Introduces elastic consistency as a general consistency model for distributed SGD.
result Derives convergence bounds for various distributed SGD methods.

Consistency distillation reduces memorization in diffusion models without harming sample quality.

problem Understanding how distillation affects memorization in diffusion models.
method Analysis of consistency distillation in diffusion models using a random feature neural network model.
result Consistency distillation reduces memorization in diffusion models without harming sample quality.

Paper tackles zero-shot translation by encouraging consistent agreement in models.

problem Challenges of generalizing multilingual translation without parallel data.
method Reformulated as probabilistic inference, introduced consistent agreement-based training.
result Agreement-based learning improves zero-shot translation by 2-3 BLEU points.

Improved unsupervised word translation using adversarial autoencoder with cycle consistency and input reconstruction.

problem Challenging language pairs and lack of parallel data for unsupervised word translation.
method Adversarial autoencoder with cycle consistency and input reconstruction regularization.
result More stable and better performance than recent approaches.

Improved neural network surrogates for ICF using manifold and cycle consistency.

problem Modeling and predicting complex physical processes in inertial confinement fusion.
method Training neural network surrogates that are consistent with the physical manifold and cyclically consistent.
result Surrogates are superior in predictive performance, more resilient to sampling artifacts, and more data efficient.

This paper improves adversarial robustness of deep learning models.

problem Vulnerability of machine learning models to adversarial perturbations.
method Analyzes adversarial training for linear regression and neural networks, incorporating L1 penalty.
result Incorporating L1 penalty leads to consistent adversarially robust estimation in high-dimensional settings.

Dissertation tackles zero-shot anomaly detection, focusing on consistent anomalies and proposing CoDeGraph framework.

problem Consistent anomalies bias distance-based zero-shot anomaly detection methods.
method Formalized consistent anomalies, identified similarity scaling and neighbor-burnout phenomena, introduced CoDeGraph framework.
result CoDeGraph effectively suppresses consistent anomalies in zero-shot anomaly detection.

Self-consistency improves the accuracy of model comparison methods.

problem Improving the accuracy of model comparison methods when simulation models are misspecified.
method Supplement traditional simulation-based training with a self-consistency loss on unlabeled real data.
result Self-consistency training improves model comparison accuracy, especially in open-world scenarios.

New method uses consistent gradient estimators for SGD in interconnected graphs.

problem Efficiently computing unbiased gradient estimators in interconnected graph scenarios.
method Uses consistent gradient estimators as an alternative to unbiased ones.
result Consistent estimators lead to the same convergence behavior as unbiased ones in various objective types.

New CycleGAN uses invertible generator for faster, less resource-intensive CT denoising.

problem Efficient unsupervised CT denoising without paired data.
method Single generator with wavelet residual domain, no discriminators, cycle consistency via invertible generator.
result Significantly improved denoising performance with faster training and less parameters.

New method interpolates training data and is consistent for various data distributions.

problem Establishing generalization guarantees for ensemble methods in the interpolating regime.
method Developed manifold-Hilbert kernel for Riemannian manifolds and used it in ensemble classification.
result Consistent ensemble classification method for broad data distributions.

A new method for weakly supervised learning that improves model accuracy.

problem Training machine learning models with precise labels is expensive; weak supervision provides a low-cost alternative.
method Data consistent weak supervision algorithm that searches over classifiers to find plausible labelings, considering features of the training data and estimating labels for low/no coverage data.
result Empirically, the method significantly outperforms state-of-the-art weak supervision methods on text and image classification tasks.

Develops methods to create consistent surrogate models for agent-based simulators.

problem High computational costs and misjudgment of interventions in agent-based models.
method Causal abstractions to learn interventionally consistent surrogate models.
result Surrogates trained for interventional consistency closely mimic the agent-based model's behavior under interventions.

NCT simplifies one-step generator adaptation to new controls.

problem Adapting one-step generators to new control conditions.
method Noise Consistency Training (NCT) integrates new controls without retraining.
result NCT achieves state-of-the-art controllable generation in a single pass.

Unified framework for certifying LLM reliability without extra supervision.

problem Improving reliability of large language models without additional supervision.
method Unified framework using majority voting and Martingale Majority Certificate (MMC).
result Certifiable inference in LLMs with statistical guarantees and adaptive stopping rules.

Improved semi-supervised learning with advanced data augmentation.

problem Enhancing deep learning models with limited labeled data.
method Substitutes simple noising operations with advanced data augmentation methods like RandAugment and back-translation.
result Achieves substantial improvements across multiple tasks and datasets.

Survey and framework for consistent uncertainty quantification in deep learning.

problem Partial uncertainty coverage and inconsistencies in deep learning uncertainty quantification.
method Bayes' theorem and conditional probability densities applied to all major sources of uncertainty.
result Improved robustness and reliability of neural network predictions in real-world scenarios.

Often the challenge associated with tasks like fraud and spam detection[1] is the lack of all likely patterns needed to train suitable supervised learning models. In order to overcome this limitation, such tasks are attempted as outlier or anomaly detection tasks. We also hypothesize that out- liers have behavioral pat…

2017-12-12abs ↗pdf ↗

PINNs struggle with data-to-PDE inconsistencies, limiting their accuracy.

problem Data inconsistency in PINNs affects their accuracy and convergence.
method Systematic analysis of PINNs with varying data fidelity and residual errors.
result PINNs saturate at an error level dictated by data inconsistency.

Diffusion models' consistency across splits explained by random matrix theory.

problem Consistency of diffusion models trained on non-overlapping subsets.
method Random matrix theory framework to quantify dataset effects on denoiser and sampling map.
result The theory explains and predicts cross-split disagreement in diffusion models.

Improved incremental sequence classification with temporal consistency.

problem Updating predictions as new sequence elements are revealed.
method Temporal-difference learning and a temporal-consistency condition for successive predictions.
result Optimizing a novel loss function improves data efficiency and predictive accuracy.

Consistent partial identification of causal effects proved for neural models.

problem Consistency of neural causal partial identification methods.
method Proving consistency for neural models with continuous and categorical variables, considering architecture design and Lipschitz regularization.
result Proven consistency of partial identification via neural causal models in a general setting.

Proposes PSGAN for generating high-res anime images with structural consistency.

problem Lack of high-quality, structurally consistent full-body high-resolution anime images.
method Progressive Structure-conditional Generative Adversarial Networks (PSGAN) with progressive training.
result Demonstrates effectiveness through comparisons and diverse anime character generation.