arXiv research

A new method for adapting to label shifts using class probability matching.

Subclass distillation improves small models by matching teacher's subclass probabilities.

New error bounds for flow matching methods using deterministic sampling.

In real-world classification problems, the class balance in the training dataset does not necessarily reflect that of the test dataset, which can cause significant estimation bias. If the class ratio of the test dataset is known, instance re-weighting or resampling allows systematical bias correction. However, learning…

Focal loss improves classification but not class-posterior probability estimation.

Paper tackles novelty detection in text classification.

New probability path model improves flow matching forecasting performance.

A new machine learning model uses score matching to estimate probability densities efficiently.

Flow Matching enables robust training of CNFs with various probability paths.

New models for analyzing microbiome data with interactions.

Study shows refugee matching gains are robust to different evaluation methods.

A common challenge in estimating parameters of probability density functions is the intractability of the normalizing constant. While in such cases maximum likelihood estimation may be implemented using numerical integration, the approach becomes computationally intensive. The score matching method of Hyvärinen [2005] …

Efficiently matches random graphs with inhomogeneous edge probabilities.

Sharp Lipschitz bounds for flow-matching and diffusion models with optimal sampling rates.

Generative adversarial networks (GANs) are an exciting alternative to algorithms for solving density estimation problems---using data to assess how likely samples are to be drawn from the same distribution. Instead of explicitly computing these probabilities, GANs learn a generator that can match the given probabilisti…

Framework generates causal probabilities from observational data.

Paper uses algebraic signatures to identify probabilistic structures in empirical data.

Algorithm identifies optimal stable matching in uncertain two-sided markets.

We analyze the problem of sequential probability assignment for binary outcomes with side information and logarithmic loss, where regret---or, redundancy---is measured with respect to a (possibly infinite) class of experts. We provide upper and lower bounds for minimax regret in terms of sequential complexities of the …

Paper studies matching of samples from two distributions with a Gibbs probability weight.

Study minimax regret in sequential probability assignment with and without side information.

Estimates class prior for unlabeled data using kernel embedding.

Improved graph matching algorithm robust to noise.

New approach for testable learning using moment matching and Rademacher complexity.

This work proposes a new method to match distributions across different spaces using cycle-consistent maps.

We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN). Our IPMs are based on matching statistics of distributions embedded in a finite dimensional feature space. Mean and covariance feature matching IPMs allow for stable training of GANs, which we will call M…

The Maximum Mutual Information (MMI) criterion is different from the Least Error Rate (LER) criterion. It can reduce failing to report small probability events. This paper introduces the Channels Matching (CM) algorithm for the MMI classifications of unseen instances. It also introduces some semantic information method…

Paper analyzes convergence of ODE samplers in Wasserstein distances.

A group of transition probability functions form a Shannon's channel whereas a group of truth functions form a semantic channel. Label learning is to let semantic channels match Shannon's channels and label selection is to let Shannon's channels match semantic channels. The Channel Matching (CM) algorithm is provided f…

We introduce a technique to compute probably approximately correct (PAC) bounds on precision and recall for matching algorithms. The bounds require some verified matches, but those matches may be used to develop the algorithms. The bounds can be applied to network reconciliation or entity resolution algorithms, which i…

Proposes DWMD for better matching of hidden representations across domains.

We consider the following conditional linear regression problem: the task is to identify both (i) a $k$-DNF condition $c$ and (ii) a linear rule $f$ such that the probability of $c$ is (approximately) at least some given bound $μ$, and $f$ minimizes the $\ell_p$ loss of predicting the target $z$ in the distribution of …

Study best arm identification with contextual info, achieving optimal misidentification probability.

The study evaluates different probability models for uncertainty visualization using entropy calculations.

A new training method for efficient Boltzmann generators.

CNFs learn on manifolds using PPD, improving likelihood and sample quality.

PPM improves graph matching for correlated Gaussian Wigner models with high probability.

New method improves domain generalization by matching object representations.

Naive Bayes can be used as a discriminative classifier, matching the definition of logistic regression.

Unified framework for continuous-state discrete flow matching models.

Paper tackles distribution matching by partially matching distributions, achieving robust results.

FFM generates functions between Gaussian and data distributions.

Experimentally, it has been observed that humans and animals often make decisions that do not maximize their expected utility, but rather choose outcomes randomly, with probability proportional to expected utility. Probability matching, as this strategy is called, is equivalent to maximum entropy reinforcement learning…

With the increasingly widespread deployment of generative models, there is a mounting need for a deeper understanding of their behaviors and limitations. In this paper, we expose the limitations of Variational Autoencoders (VAEs), which consistently fail to learn marginal distributions in both latent and visible spaces…

In real supervised learning scenarios, it is not uncommon that the training and test sample follow different probability distributions, thus rendering the necessity to correct the sampling bias. Focusing on a particular covariate shift problem, we derive high probability confidence bounds for the kernel mean matching (…

The learning of domain-invariant representations in the context of domain adaptation with neural networks is considered. We propose a new regularization method that minimizes the discrepancy between domain-specific latent feature representations directly in the hidden activation space. Although some standard distributi…

Flow matching improves synthetic data generation for tabular data.

Increasing availability of vehicle GPS data has created potentially transformative opportunities for traffic management, route planning and other location-based services. Critical to the utility of the data is their accuracy. Map-matching is the process of improving the accuracy by aligning GPS data with the road netwo…