Bi-Lipschitz flows approximate a wide range of distributions.
problem Characterizing the expressivity of bi-Lipschitz normalizing flows.
method Linking score regularity to transport map bi-Lipschitzness via probability flow ODE.
result Gaussian pullbacks induced by bi-Lipschitz variance-preserving transport maps are L1-dense among all probability densities. OTCP extends conformal prediction to multivariate data using optimal transport.
problem Uncertainty quantification in multivariate machine learning models.
method OTCP leverages optimal transport to rank multivariate conformity scores.
result Preserves distribution-free coverage guarantees in multidimensional settings.
Introduces VSMD to improve generative diffusion processes without high costs.
problem High training costs and scalability issues in generative diffusion processes.
method Introduces variational Schrödinger momentum diffusion (VSMD) with adaptively transport-optimized variational scores and critical-damping transform.
result Efficiently generates anisotropic shapes while maintaining transport efficacy, outperforming alternatives.
New optimal transport divergences derived from scoring functions.
problem Developing new divergences for optimal transport.
method Using scoring functions as cost functions in optimal transport.
result Comonotonic coupling is optimal for many new divergences.
TSC uses HMC and adaptive transport maps to optimize forward KL for variational inference.
problem Variational inference underestimates uncertainty when minimizing reverse KL.
method TSC uses Hamiltonian Monte Carlo and adaptive transport maps to optimize KL(p||q).
result TSC achieves competitive performance in training variational autoencoders on large-scale data.
Algorithm learns non-Gaussian graphical models via Hessian scores and triangular transport.
problem Learning graph structure from non-Gaussian data.
method Score based on integrated Hessian information, coupled with triangular transport map.
result Algorithm successfully recovers graph structure for non-Gaussian data.
TRACE improves conformal prediction for multi-dimensional outputs.
problem Challenges in constructing valid and informative conformal prediction regions for multi-dimensional outputs.
method TRACE uses transport alignment in diffusion and flow matching models to define nonconformity scores.
result TRACE yields valid and adaptive conformal prediction regions for multimodal and non-convex distributions.
SPI uses synthetic data to improve predictive inference efficiency.
problem Inefficient predictive inference with scarce calibration data.
method Integrates synthetic data to align nonconformity scores and improve coverage guarantees.
result SPI yields substantially tighter and more informative prediction sets.
New method extends conformal prediction to multivariate settings using optimal transport.
problem Limited applicability of conformal prediction to multivariate real-valued scores.
method Use optimal transport to define vector-ranks and multivariate quantile regions for finite-sample coverage.
result Constructs the first multivariate conformal predictive distributions with finite-sample calibration.
FairPOT balances fairness and AUC performance by selectively transforming risk scores.
problem Balancing fairness and AUC performance in high-stakes domains.
method FairPOT uses proportional optimal transport to selectively transform risk scores.
result FairPOT consistently improves fairness with minimal AUC degradation or even positive gains.
The paper constructs denoisers that recover the Brenier map from higher-order score functions.
problem Estimating the Brenier map from noisy data.
method Constructs a hierarchy of denoisers using higher-order score functions.
result The T∞ denoiser recovers the Brenier map from the additive Gaussian model. Framework uses optimal transport to quantify model risk in stochastic path laws.
problem Model risk in stochastic path laws.
method Signature-induced optimal transport framework.
result Explicit robust bounds and budget-aware sparse surrogate method.
OTF uses optimal transport to measure classifier fairness.
problem Measuring and reducing unfairness in classifier predictions.
method Introduces Optimal Transport to Fairness (OTF) to quantify and reduce unfairness.
result OTF improves the balance between classifier performance and fairness.
A new OOD detection method OTOD uses optimal transport theory to improve model performance.
problem Detecting unknown samples in real-world machine learning models.
method OTOD uses optimal transport theory to calculate an OOD score combining features, logits, and softmax probability space.
result OTOD outperforms state-of-the-art methods by significant margins on benchmarks.
MAGT generates data efficiently by aligning to manifold structure.
problem Efficiently generating data near a low-dimensional structure embedded in high-dimensional space.
method MAGT is a flow-like generator that learns a one-shot, manifold-aligned transport from a low-dimensional base distribution to the data space, using a fixed Gaussian smoothing level and self-normalized importance sampling.
result MAGT samples in a single forward pass, concentrates probability near the learned support, and induces an intrinsic density with respect to the manifold volume measure, enabling principled likelihood evaluation for generated samples.
A novel approach for semi-supervised learning using regularized optimal transport.
problem Improving model performance with unlabeled data.
method Regularized optimal transport between empirical measures for affinity matrix construction, incremental label propagation, and certainty score.
result Surpasses state-of-the-art results on 12 benchmark datasets.
New method improves posterior sampling for complex data models.
problem Sampling from posterior distributions in high-dimensional data.
method Tilted transport technique combining denoising oracle and log-likelihood.
result Boosted posterior is strongly log-concave, facilitating easier sampling.
New algorithm detects anomalies by forcing samples to displace mass in low-density regions.
problem Detecting anomalies in datasets.
method Mass Repulsing Optimal Transport (MROT) approach.
result Our algorithm improves anomaly detection over existing methods.
Optimal transport improves multivariate prediction uncertainty quantification.
problem Uncertainty quantification in multivariate learning tasks, especially in regression and classification.
method Introducing a novel Conformal Prediction procedure using optimal transport to handle multivariate score functions and construct flexible prediction regions.
result Ensures finite-sample, distribution-free coverage guarantees for multivariate prediction sets.
ResNets learn the geodesic curve in Wasserstein space.
problem Characterize the dynamics of deep residual networks during training.
method Modeling ResNet dynamics using continuity equations and optimal transport.
result ResNets learn the geodesic curve in the Wasserstein space.
Stein transport improves Bayesian inference with faster convergence and reduced variance.
problem Efficiently approximating posterior distributions in Bayesian inference.
method A novel Bayesian inference method using Stein transport, which pushes particles along a curve of tempered distributions.
result Stein transport reaches posterior approximations faster and more accurately than Stein variational gradient descent (SVGD).
Within a broad class of generative adversarial networks, we show that discriminator optimization process increases a lower bound of the dual cost function for the Wasserstein distance between the target distribution p and the generator distribution pG. It implies that the trained discriminator can approximate opti…
New method distinguishes cause from effect using causal velocity.
problem Inferring causal direction from bivariate data.
method Parametrization of bivariate SCMs in terms of causal velocity, using tools from measure transport.
result Method extends beyond known model classes and requires no assumptions on noise distributions.
DSB approximates SB problem for faster generative modeling.
problem Fast generation from complex data distributions.
method Entropy-regularized optimal transport on path spaces.
result DSB yields faster convergence to data distribution.
The top-k operation, i.e., finding the k largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining. However, if the top-k operation is implemented in an algorithmic way, e.g., using bubble algorithm, the re…
Multi-language speech datasets are scarce and often have small sample sizes in the medical domain. Robust transfer of linguistic features across languages could improve rates of early diagnosis and therapy for speakers of low-resource languages when detecting health conditions from speech. We utilize out-of-domain, unp…
CMCD sampler connects transport and variational inference for efficient sampling.
problem Efficient sampling and generative modeling in Bayesian computation.
method Developed a principled framework using divergences on path space, CMCD sampler with adaptive dynamics.
result CMCD sampler outperforms competing approaches across various experiments.
This paper tackles denoising of complex measures using optimal transport and curvature analysis.
problem Denoising of complex, possibly non-log-concave measures.
method Score function and optimal transport theory to revert Langevin diffusion chains.
result The difficulty of denoising depends on the curvature complexity of the initial measure at specific SNR scales.
The ability to measure similarity between documents enables intelligent summarization and analysis of large corpora. Past distances between documents suffer from either an inability to incorporate semantic similarities between words or from scalability issues. As an alternative, we introduce hierarchical optimal transp…
Generative models help make decisions under changing data distributions.
problem Making decisions based on historical data when the actual data distribution changes.
method Flow- and score-based generative models to represent and transform distributions.
result Generative models can learn nominal uncertainty, create stressed distributions, and produce conditional distributions.
Paper presents a method to align unpaired samples across different modalities.
problem Challenges in collecting paired samples for multimodal representation learning.
method Uses propensity score alignment based on Rubin's framework to estimate a common space for unpaired samples.
result Optimal transport matching significantly improves alignment in real-world data.
Proposes a method to infer the distributional impacts of predictive models on stakeholders.
problem The influence of predictive models on target variable distribution, leading to performative prediction.
method Modeling agents' responses as a cost-adjusted utility maximization problem and using optimal transport to align pre- and post-model distributions.
result Provides estimates for the cost associated with these responses and demonstrates the quality of these estimates.
PDDS samples from unnormalized densities using iterative particle scheme.
problem Sampling from unnormalized probability densities.
method Iterative particle scheme with novel score matching loss.
result Asymptotically consistent estimates for multimodal and high-dimensional tasks.
Unified approach to denoising Markov models for efficient sampling.
problem Designing efficient sampling algorithms for complex distributions.
method Mathematical foundation using measure transport and nonequilibrium statistical mechanics.
result Unified variational objective and backward generator construction.
IGSD separates task-specific content channels in transformer components by comparing activation replacement with zero ablation.
problem Mechanistic interpretability of transformer components
method IGSD: paired-intervention framework for comparing activation replacement with zero ablation
result IGSD identifies an early-layer content channel in transformer components that standard importance methods underestimate.
A new method ranks uncertainty vectors from multiple measures for robust prediction.
problem Single scalar measures of model reliability are insufficient for comprehensive uncertainty quantification.
method Optimal transport ranks vectors of uncertainty measures, supporting flexible fusion of aleatoric and epistemic uncertainties.
result The method provides a robust ranking of uncertainty that supports various downstream tasks.
Method aligns multilingual news for better stock return prediction.
problem Losing nuances in multilingual news translations.
method Optimal transport for sentence alignment.
result Aligned sentences correlate better with stock returns.
New framework uses PDE for no-regret generative modeling.
problem Developing efficient generative models for complex distributions.
method Iterative refinement of Brenier maps using mirror gradient descent.
result Converges to optimal Brenier map under various step-size schedules.
A novel diffusion method for Bayesian posterior sampling with theoretical guarantees.
problem Efficiently sampling from complex posterior distributions in Bayesian inversion.
method Diffusion-based posterior sampling using Langevin dynamics and PnP framework.
result The method converges even for multi-modal posterior distributions with theoretical error bounds.
The study connects fairness constraints with optimal transport to derive new insights in classification.
problem Ensuring fairness in classification models without sacrificing performance.
method Using Wasserstein barycenters and optimal transport, the study characterizes optimal classification functions under fairness constraints.
result Maximizing fairness under demographic parity is equivalent to solving a regression problem.
TimeLAVA learns time series segment values without model dependence.
problem Valuation of time series data for critical domains.
method Learning-agnostic framework using Selective Wavelet-based Wasserstein discrepancy.
result TimeLAVA produces more informative value scores than existing methods.
Unified framework for robust, stable, and efficient density ratio estimation.
problem Density-chasm and support-chasm problems in density ratio estimation.
method Dequantified diffusion-Schrödinger bridge (D3RE) framework with DDBI and DSBI.
result Offers uniform approximation and bounded time scores in theory and empirical performance.
A new method corrects bias in causal inference by balancing covariate distributions.
problem Bias in causal effect estimates due to covariate imbalance.
method Causal Optimal Transport, a nonparametric approach targeting distributional balance.
result Causal Optimal Transport outperforms other methods in misspecified models.
This paper optimizes diffusion schedules for better sampling from data distributions.
problem Choosing an optimal discretization schedule for denoising diffusion models.
method Adaptive algorithm that selects an optimal schedule based on a work cost measure.
result The learned schedule recovers and outperforms manually tuned schedules.
Sharp 2-Wasserstein bounds for DDPMs derived from Föllmer process.
problem Sampling error bounds for DDPMs in 2-Wasserstein distance.
method Lipschitz-type conditions on score function, Föllmer process, and log-concave target distributions.
result Sharp upper bounds for DDPMs in 2-Wasserstein distance, optimal in dimension and steps.
CJE calibrates cheap LLM judges against an oracle, achieving high accuracy at a fraction of the cost.
problem Inexpensive LLM judges can produce biased rankings, leading to unreliable outcomes.
method CJE uses a small oracle to calibrate cheap scores, then evaluates at scale with valid uncertainty.
result CJE achieves 99% pairwise ranking accuracy at 14x lower cost compared to a 16x oracle/judge cost ratio.
Paper introduces non-linearity signature to measure deep neural network performance.
problem Difficulty in explaining performance differences among similar DNN architectures.
method Affine Optimal Transport mappings to measure non-linearity.
result Signature provides better understanding of DNN inner workings.
Study improves traffic prediction intervals for minor roads.
problem Uncertainty in traffic data for underrepresented minor roads.
method Quantile Random Forest with PCA for interval prediction.
result Achieved 88.22% interval coverage and Winkler Score of 7,468.47.