The paper improves experimental design by weighting diversity metrics with quality, leading to more diverse and effective discoveries.
problem Existing experimental design techniques favor exploitation over exploration, leading to local optima and insufficient diversity.
method The paper extends Vendi scores to account for quality and applies them to various experimental design problems.
result Quality-weighted Vendi scores allow for better balance between quality and diversity, resulting in 70%-170% more effective discoveries.
This study examines ensembling of diffusion models for improved generative quality.
problem Improving generative quality with ensembling of score-based diffusion models.
method Investigated ensembling of scores from multiple diffusion models on image and tabular data.
result Ensembling scores generally improves model likelihood and score-matching loss but not perceptual quality metrics.
Accelerates data generation in score-based models.
problem Slow generation of realistic data by score-based models.
method Developed an adaptive step size SDE solver.
result Generates data 2-10 times faster with high quality.
We propose a training method for deep neural network (DNN)-based source enhancement to increase objective sound quality assessment (OSQA) scores such as the perceptual evaluation of speech quality (PESQ). In many conventional studies, DNNs have been used as a mapping function to estimate time-frequency masks and traine…
Stabilizes training of DNN for speech enhancement using PESQ scores.
problem Stability issues in training DNNs using non-differentiable OSQA scores.
method Approximate OSQA scores with a differentiable auxiliary DNN and stabilize training with reinforcement learning techniques.
result Stable training of DNN to achieve state-of-the-art PESQ scores and better sound quality.
Unified model combines scores and rankings for grant panel review.
problem Combining scores and rankings for quality assessment in panel review.
method Mallows-Binomial model with tree-search algorithm for exact MLE.
result Model combines scores and rankings to quantify object quality and measure consensus.
High-quality image synthesis with diffusion models, achieving state-of-the-art FID score.
problem Generating high-quality images from latent variables.
method Training diffusion probabilistic models with a weighted variational bound, inspired by denoising score matching and Langevin dynamics.
result State-of-the-art FID score of 3.17 on CIFAR10 dataset.
CTM improves diffusion model sampling quality with efficient ODE traversal.
problem Lack of natural trade-off between sample quality and speed in consistency models.
method CTM trains a neural network to output scores and traverse ODE trajectories efficiently.
result CTM achieves state-of-the-art FIDs and improves sample quality with increased computational budget.
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
problem Evaluation of GANs for sample quality and diversity.
method Integrates various factors including intra-class and inter-class diversity, disentanglement, and discriminability metrics.
result Demonstrates improved evaluation of GANs on MNIST dataset.
New bounds close the score matching gap for diffusion models.
problem The difference between sample quality and score matching loss in diffusion models.
method Theoretical analysis of score matching gap, developing tighter bounds for KL divergence, reverse KL divergence, and Wasserstein distance.
result The quality of score approximation impacts closing the score matching gap for low noise scales.
Improves image quality in generative models by estimating pixel-wise aleatoric uncertainty.
problem Lack of quantitative assessment of image quality in diffusion models.
method Estimate pixel-wise aleatoric uncertainty during sampling phase using a perturbation scheme designed for diffusion models.
result Uncertainty-guided sampling leads to better sample generation quality as shown by FID scores.
VLM judges rank well but score poorly; task difficulty and annotation quality affect interval width.
problem VLMs as judges lack reliability indicators in multimodal evaluations.
method Conformal prediction using score-token log-probabilities.
result Evaluation uncertainty is task-dependent, affecting interval width and reliability.
A new method improves data generation quality by correcting score mismatches.
problem Score mismatch issue in conditional score-based data generation methods.
method Denoising Likelihood Score Matching (DLSM) loss for classifier training.
result The proposed method outperforms previous methods on Cifar-10 and Cifar-100 benchmarks.
Improved image compression with diffusion models outperforming state-of-the-art methods.
problem Difficulties in replicating text-to-image success in image compression.
method Two-stage approach combining autoencoder targeting MSE followed by score-based decoder.
result Significantly improved perceptual quality at a given bit-rate, measured by FID score.
Improved score-based models generate high-quality images up to 256x256.
problem Training score-based models for high-resolution images is unstable and limited.
method Theoretical analysis, exponential moving average of model weights.
result Score-based models can generate high-fidelity images up to 256x256.
This work improves likelihood of score-based diffusion ODEs using high-order denoising score matching.
problem The gap between maximum likelihood and score matching objectives for score-based diffusion ODEs.
method High-order denoising score matching to maximize likelihood.
result Score-based diffusion ODEs achieve better likelihood on synthetic and CIFAR-10 data.
Score matching method improves image generation quality.
problem Score matching method underperforms GANs in metrics like Fréchet Inception Distance.
method DSM-ALS with denoising and improved sampling techniques.
result Score matching methods can match GANs in image generation quality.
ProSMIN improves representation quality through probabilistic self-supervised learning.
problem Improving representation quality in self-supervised learning.
method ProSMIN uses two neural networks, online and target, to learn diverse representations through knowledge distillation and a modified scoring rule loss function.
result ProSMIN achieves superior accuracy and calibration on various downstream tasks.
Score matching errors are not sufficient for measuring diffusion model quality.
problem The L2 score matching error is not a reliable measure of diffusion model performance. method Decomposed score errors into gradient and solenoidal components and analyzed their geometric properties.
result Only the gradient component of the score error affects the marginal distributional quality.
We present RUSLAN -- a new open Russian spoken language corpus for the text-to-speech task. RUSLAN contains 22200 audio samples with text annotations -- more than 31 hours of high-quality speech of one person -- being the largest annotated Russian corpus in terms of speech duration for a single speaker. We trained an e…
SDM Policy accelerates inference for robotic tasks while maintaining high action quality.
problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.
The paper introduces a method to assess machine translation quality with confidence intervals.
problem Evaluating the uncertainty and quality of machine translation.
method Utilizes conformal predictive distributions to produce prediction intervals with guaranteed coverage.
result The method outperforms a baseline on six language pairs in terms of coverage and sharpness.
A new method for diffusion generative models improves sample quality and speed.
problem Improving the efficiency and quality of diffusion generative models.
method Developed a complete recipe for forward diffusion processes in SGMs, introducing PSLD.
result PSLD achieves superior sample quality and speed compared to existing methods.
New method boosts performance of diffusion models on discrete data like natural language.
problem Performance of diffusion models on discrete data like natural language is poor.
method Proposes score entropy, a novel loss that extends score matching to discrete spaces.
result Significantly boosts performance on language modeling tasks.
Paper uses SSL models' uncertainty to predict audio quality efficiently.
problem Efficiently predicting audio quality in low-resource settings.
method Leverages self-supervised learning models' uncertainty measures.
result Uncertainty measures correlate with MOS scores in SSL models.
DreamPropeller accelerates text-to-3D generation by 4.7x with minimal loss in quality.
problem Long generation times in text-to-3D generation algorithms degrade user experience.
method DreamPropeller uses Picard iterations generalized for non-ODE paths to accelerate parallel sampling.
result Empirically achieves up to 4.7x speedup with negligible quality loss.
Credit scores misclassify borrowers, especially minorities, leading to inequitable access.
problem Misclassification of borrowers by credit scores, particularly minorities.
method Benchmarked a widely used credit score against a machine learning model.
result Machine learning model improves predictive accuracy for low-quality data, leading to more equitable access.
Class labels have been empirically shown useful in improving the sample quality of generative adversarial nets (GANs). In this paper, we mathematically study the properties of the current variants of GANs that make use of class label information. With class aware gradient and cross-entropy decomposition, we reveal how …
Compressing word embeddings is important for deploying NLP models in memory-constrained settings. However, understanding what makes compressed embeddings perform well on downstream tasks is challenging---existing measures of compression quality often fail to distinguish between embeddings that perform well and those th…
This paper argues against using calibration metrics for assessing posterior probabilities and proposes expected proper scoring rules instead.
problem The assessment of posterior probabilities generated by machine learning classifiers using calibration metrics is flawed and should be replaced with expected proper scoring rules.
method The paper reviews proper scoring rules from a practical perspective, explains why expected PSRs are a principled measure of posterior quality, and introduces a new calibration metric called calibration loss.
result Calibration loss is superior to expected calibration error and expected score divergence calibration metrics for assessing posterior probabilities.
Proposes qIS for quantum generative models, extending classical inception score.
problem Develop a metric to evaluate quantum generative models.
method Introduces qIS, relating quality to Holevo information of quantum channel.
result qIS enhances the quality of quantum generative models, showing physical limitations.
Generative models have made immense progress in recent years, particularly in their ability to generate high quality images. However, that quality has been difficult to evaluate rigorously, with evaluation dominated by heuristic approaches that do not correlate well with human judgment, such as the Inception Score and …
New geometric analysis shows L2 score error is flawed for diffusion models.
problem Score matching errors in diffusion models do not fully capture distributional quality.
method Decomposed score errors into gradient and solenoidal components, focusing on gradient's role in Fokker-Planck dynamics.
result Only gradient component affects marginal distributional quality; solenoidal component is structurally invisible.
Optimal score function estimation via empirical risk minimization
problem Estimating the score function of a probability measure on the flat torus from a sample
method Constraining the hypothesis space to a Sobolev ball
result Minimax estimation rates are achieved
Improved GEC models use scored data from large pretraining to outperform.
problem Addressing data sparsity in Grammatical Error Correction.
method Derive example-level scores from a smaller, higher-quality dataset and incorporate delta-log-perplexity into training schedules.
result Models trained on scored data achieve state-of-the-art results.
Improves sampling quality in model composition using MH-like acceptance rule for score-based diffusion models.
problem Inability to apply MH corrections in score-based diffusion models for model composition.
method Introduces a novel MH-like acceptance rule based on line integration of the score function.
result Relative improvements similar to energy-based models without explicit energy parameterization.
New method improves quality and efficiency of generative models by using smaller diffusion times.
problem Lack of theoretical understanding of diffusion time T in score-based diffusion models.
method Introduce an auxiliary model to bridge the gap between ideal and simulated dynamics, followed by reverse diffusion.
result Empirical results show competitive performance in image data compared to state-of-the-art models.
Generative models need per-sample confidence scores to improve quality and stability.
problem Generative models produce unreliable outputs and lack confidence measures.
method Flow Matching with Confidence (FMwC) injects noise and integrates it through the network, providing per-sample confidence scores.
result The confidence score correlates with the velocity field's divergence, offering insights into generative processes.
Unified framework for SDMs and GANs with improved sampling and quality.
problem Limitations of SDMs and GANs in achieving fast sampling and high sample quality.
method Introducing a novel SDE named DiffFlow to describe the learning dynamics of SDMs and GANs, and proving the asymptotic optimality and maximal likelihood training scheme.
result Unified framework allows smooth transition between SDMs and GANs with flexible trade-off between sample quality and speed.
Improved autoregressive models generate higher quality images and are more robust to noise.
problem Generating high-quality images from autoregressive models.
method Noise conditional maximum likelihood estimation (MLE) with score-based sampling.
result Models trained with noise conditional MLE achieve better test likelihoods and generate higher quality images.
Early stopping improves sample quality in latent diffusion models.
problem Latent diffusion models degrade sample quality with conventional early stopping.
method Analyzed the interaction between latent dimension and stopping time under Gaussian framework.
result Lower-dimensional representations benefit from earlier termination, higher-dimensional spaces require later stopping.
A new method for generating synthetic data using posterior distribution learning accelerates inference.
problem Generating high-quality synthetic data requires many discretization steps, which is computationally expensive.
method Learning the posterior distribution of clean data samples given noisy versions, using a scoring rule instead of regression loss.
result Consistently outperforms standard diffusion models at few discretization steps.
Improved GAN training speed and quality with FastGAN.
problem Slower convergence and less expressive models in GAN training.
method Adversarial training with FastGAN algorithm.
result Better generation quality with less training time.
Generative models improved with smoothed score functions for better sample quality.
problem Improving generative models for better sample quality.
method Smoothed score functions based on factorial Gaussian kernels.
result Single noise level achieved 14.15 Fréchet inception distance on CIFAR-10.
Credit Scores are ubiquitous and instrumental for loan providers and regulators. In this paper we showcase how micro-loan credit system can be developed in real setting. We show what challenges arise and discuss solutions. Particularly, we are concerned about model interpretability and data quality. In the final sectio…
Improved sampling quality with RBM-Flow and D-Flow models.
problem Efficient sampling of complex data distributions using invertible flows.
method Implement RBM-Flow and D-Flow models with discrete latent variables.
result Significant improvement in sampling quality over baseline models.
Computer-aided assessment of physical rehabilitation entails evaluation of patient performance in completing prescribed rehabilitation exercises, based on processing movement data captured with a sensory system. Despite the essential role of rehabilitation assessment toward improved patient outcomes and reduced healthc…
Study reveals bias in machine learning conference reviews.
problem Bias in machine learning conference review process.
method Comprehensive analysis of ICLR papers from 2017-2020.
result Strong institutional bias in accept/reject decisions.