LLM safety alignment explained as divergence estimation.
problem Aligning large language models to avoid harmful outputs.
method Presented a theoretical framework showing alignment methods as divergence estimators.
result KLDO method improves safety alignment using compliance-refusal datasets.
Fuses posterior distributions from different datasets using KL divergence.
problem Combining information from multiple datasets with uncertainty.
method Mean field assumption, KL divergence, assign-and-average approach.
result Efficient non-parametric algorithm for fused model computation.
Paper develops a method to compare generative models using KL divergence.
problem Lack of principled uncertainty quantification for generative models.
method Employ Kullback-Leibler divergence to measure generative model distance.
result Effective coverage rates and higher power compared to kernel-based methods.
New estimator improves reliability of KL divergence estimation.
problem Estimating KL divergence reliably and efficiently.
method Proposes a new estimator using Reproducing Kernel Hilbert Space.
result Proposed estimator is consistent and more reliable for small datasets.
New framework using Jensen-Shannon divergence improves domain adaptation theory.
problem Incoherence between empirical domain adversarial training and theoretical H-divergence. method Established new theoretical framework based on Jensen-Shannon divergence, derived bi-directional upper bounds.
result Framework exhibits flexibilities for various transfer learning problems.
New algorithm speeds up NMF with β-divergence.
problem Efficiently factorize nonnegative matrices with β-divergence. method Joint majorization-minimization with multiplicative updates.
result Significant reduction in computation time for NMF.
New method to measure compositional generalization on realistic data.
problem Limited compositional generalization in machine learning.
method Maximizing compound divergence while ensuring small atom divergence.
result Machine learning architectures fail to generalize compositionally.
Unified deep metric learning approach using neural networks.
problem Learning embeddings of data and extending Euclidean distances.
method Deep Bregman divergences based on neural networks.
result Superior performance on benchmark datasets compared to existing methods.
Develops deep NMF models using β-divergences for feature extraction.
problem Inadequate evaluation metrics for deep NMF on diverse datasets.
method Introduces new deep NMF models using Kullback-Leibler divergence.
result Improves feature extraction quality across different types of data.
Machine learning classification limits estimated using Kullback-Leibler divergence and Cohen's Kappa.
problem Estimating the best possible performance of machine learning classification algorithms.
method Relating Kullback-Leibler divergence to Cohen's Kappa and using the Chernoff-Stein Lemma to estimate error rates.
result Classification algorithms could not have performed any better due to underlying probability density functions for the two classes.
A new robust PCA estimator combining M-estimators and minimum divergence estimators.
problem Adverse effect of outlying observations in PCA for high-dimensional data.
method Minimum density power divergence estimator combined with a computationally efficient algorithm.
result High breakdown guarantee regardless of data dimension with theoretical support and practical applications.
Paper introduces a new method for learning Bregman divergence from data.
problem Suboptimal performance of classic distance metrics in deep metric learning.
method Learning empirical Bregman divergence from data using deep learning.
result Empirical Bregman divergence method outperforms other methods on public datasets.
Approaches KL divergence for learning multi-sense word distributions.
problem Capturing the polysemy and uncertainty of words in word embeddings.
method Modeling words as multi-sense Gaussian mixtures and using KL divergence for learning.
result The proposed approach effectively captures word entailment and distribution similarity.
Fisher auto-encoders use Fisher divergence for more robust generative modeling.
problem Model uncertainty in generative models.
method Minimizing Fisher divergence between true and modeled joint distributions.
result Fisher auto-encoders can more accurately quantify model uncertainty.
A new differentiable divergence for time series comparison.
problem Computing discrepancies between time series of varying lengths.
method Proposed a new divergence, soft-DTW divergence, addressing issues of differentiability and positivity.
result Showed that the new divergence is a valid divergence: non-negative and minimized when time series are equal.
New divergences improve estimation and GAN training performance.
problem Improving estimation and training in machine learning models.
method Function-space regularized Rényi divergences.
result New divergences reduce variance and improve training performance.
Improved VAE for heavy-tailed data using Student's t-distributions.
problem Over-regularization in VAEs with Gaussian priors.
method Proposed t3VAE framework with Student's t-distributions for prior, encoder, and decoder. result Significantly outperforms other models on heavy-tailed datasets.
Efficiently visualizes uncertainty in local divergence of 2D vector fields.
problem Uncertainty in vector field data leads to inaccurate divergence computations.
method Closed-form approach for highly efficient and accurate uncertainty visualization of local divergence, assuming independently Gaussian-distributed vector uncertainties.
result Significantly enhanced efficiency and accuracy of our algorithms over classical MC approach.
There has been a growing interest in mutual information measures due to their wide range of applications in Machine Learning and Computer Vision. In this paper, we present a generalized structured regression framework based on Shama-Mittal divergence, a relative entropy measure, which is introduced to the Machine Learn…
Proposes a generative model using scaled-Bregman divergences to handle support mismatch in training.
problem Support mismatch between model and data distributions during training.
method Augments the base measure of the problematic divergence (scaled-Bregman) to resolve the support mismatch problem.
result Demonstrates promising results on MNIST, CelebA, and CIFAR-10 datasets.
A method to compute divergences between decomposable models, useful in supervised learning.
problem Computing exact divergences between high-dimensional distributions is intractable.
method Proposes an approach to compute exact alpha-beta divergences between marginal and conditional distributions of decomposable models.
result Tractable computation of marginal and conditional alpha-beta divergences.
Paper introduces a diagnostic for approximate inference methods.
problem Estimating errors in probabilistic inference algorithms, especially for approximate methods.
method Repeatedly simulate datasets from the prior and perform inference on each, estimating a symmetric KL-divergence.
result A diagnostic for approximate inference methods can be estimated using symmetric KL-divergence.
The objective of change-point detection is to discover abrupt property changes lying behind time-series data. In this paper, we present a novel statistical change-point detection algorithm based on non-parametric divergence estimation between time-series samples from two retrospective segments. Our method uses the rela…
We study Eγ-divergence contraction and its privacy implications.
problem Analyzing privacy in data processing and algorithms.
method Generalizing Dobrushin's coefficient to Eγ-divergence and deriving contraction coefficients. result Local differential privacy can be expressed in terms of Eγ-divergence contraction, leading to precise sample size reductions. A study on α-GANs proving convergence and estimation guarantees.
problem Analyzing the convergence and estimation guarantees of α-GANs. method Proved a correspondence between α-GANs and f-divergences, and provided estimation bounds. result Estimation bounds indicate diverse GAN behavior as a function of α. Study compares chi-squared divergence and KL-divergence posteriors for PAC-Bayesian bounds.
problem Investigates optimal posteriors for PAC-Bayesian bounds using chi-squared divergence.
method Analyzes bounds for three distance functions, derives FP equations for computation.
result Chi-squared divergence based posteriors have weaker bounds and worse test errors.
Robust VAE improves model performance on corrupted data.
problem Outliers in training data degrade model performance.
method Applying robust statistics to VAEs using beta-divergence.
result Improved robustness to outliers in generated representations.
t-SNE algorithm's points remain bounded under gradient flow.
problem Understanding the boundedness of t-SNE points.
method Gradient flow of t-SNE with KL divergence, examining weak convergence assumptions.
result Points generated by t-SNE remain bounded under gradient flow.
FedMAX tackles activation divergence in FL, improving accuracy and efficiency.
problem Activation divergence in Federated Learning due to non-IID data.
method Introduced a prior based on maximum entropy to minimize information about per-device activation vectors and make similar classes more alike.
result Significantly more similar activation vectors across multiple devices, leading to better accuracy and efficiency.
AutoTransfer improves subject transfer learning for biosignal datasets.
problem Subject transfer learning for challenging biosignal datasets.
method Regularization framework with mutual information or divergence penalties.
result Improves subject transfer learning performance on EEG, EMG, and ECoG datasets.
PSDR improves robustness against noisy labels by penalizing KL divergence between similar inputs.
problem Robust training of DNNs in datasets with noisy labels.
method Introduces PSDR, a manifold regularizer that penalizes KL divergence between similar inputs.
result Significantly improves robustness against noisy labels on benchmark datasets.
CAKD framework optimizes knowledge transfer by focusing on influential components of distillation.
problem Balancing and optimizing knowledge transfer in distillation models.
method Decouple KL divergence into BCD, SCD, and WCD; prioritize influential components.
result CAKD framework consistently outperforms baseline across diverse models and datasets.
A new approach to model rejection using density ratios.
problem Improving model performance through selective prediction.
method Optimization of a loss's risk with φ-divergence regularization to find an idealized data distribution.
result Model rejection can be made by comparing the density ratio of the idealized distribution to the actual data distribution.
The paper introduces a new method for estimating optimal policies in dynamic treatment regimes using information geometry.
problem Estimating optimal policies in dynamic treatment regimes.
method Minimum information divergence method based on γ-power divergence. result The γ-power divergence method effectively seeks the optimal policy by vanishing the divergence between policy-equivalent Q-functions. Unified framework for high-dimensional online learning with non-divergent error bounds and adaptive gains.
problem Divergence of error bounds in high-dimensional online learning as data batches increase.
method Asynchronous decomposition framework with summary statistics and dynamic regularization.
result Non-divergent error bounds and adaptive gains in sparse online optimization.
The Dirichlet mechanism protects privacy while minimizing KL divergence.
problem Minimizing KL divergence while protecting sensitive data privacy.
method Using the exponential mechanism with the KL divergence loss function, resulting in the Dirichlet mechanism.
result Proved a probability tail bound on KL divergence and derived a lower bound for sample complexity.
New method learns disentangled signals without prior or model constraints.
problem Learning disentangled signals from data without prior or model constraints.
method Minimizes conditional KL divergence using a sequential algorithm to learn de-mixing flow models.
result Method learns self-sufficient signals that can reconstruct missing values.
Proposes ATM method to improve domain adaptation.
problem Mitigating distribution divergence between source and target domains.
method Adversarial Tight Match (ATM) method using Maximum Density Divergence (MDD).
result New state-of-the-art performance on domain adaptation benchmarks.
This paper introduces a novel approach for learning to rank (LETOR) based on the notion of monotone retargeting. It involves minimizing a divergence between all monotonic increasing transformations of the training scores and a parameterized prediction function. The minimization is both over the transformations as well …
Generative adversarial networks (GANs) can be interpreted as an adversarial game between two players, a discriminator D and a generator G, in which D learns to classify real from fake data and G learns to generate realistic data by "fooling" D into thinking that fake data is actually real data. Currently, a dominating …
Paper develops robust Bayesian models for linear regression under adversarial perturbations.
problem Ensuring reliable machine learning models under data perturbations.
method Formulates adversarial Bregman divergence loss, computes adversarial perturbation, introduces adversarially robust posteriors, derives generalization certificates.
result Derives first rigorous generalization certificates for adversarially robust Bayesian linear regression.
New method tightens variational representations of divergences for faster learning.
problem Improving tightness of variational representations of divergences for faster statistical estimation.
method Improved objective functionals constructed via an auxiliary optimization problem, leveraging neural network approximation.
result Tighter variational representations can result in significantly faster learning and more accurate estimation of divergences.
Black-box alpha (BB-α) is a new approximate inference method based on the minimization of α-divergences. BB-α scales to large datasets because it can be implemented using stochastic gradient descent. BB-α can be applied to complex probabilistic models with little effort since it only requires as input the likel…
This paper addresses the estimation of the latent dimensionality in nonnegative matrix factorization (NMF) with the β-divergence. The β-divergence is a family of cost functions that includes the squared Euclidean distance, Kullback-Leibler and Itakura-Saito divergences as special cases. Learning the model order is impo…
New privacy model limits adversary's function class size.
problem Measuring privacy risk in differential privacy.
method Introduces capacity bounded differential privacy, limits adversary's function class size.
result New privacy model limits adversary's function class size.
This paper proposes a more efficient training method for energy-based models.
problem The computational burden and validity trade-off in Contrastive Divergence training.
method Introducing Diffusion Contrastive Divergence (DCD) to replace Langevin dynamics with diffusion processes.
result The proposed DCDs are more computationally efficient and handle gradient terms better than Contrastive Divergence.
Enhanced 3D shape analysis using information geometry.
problem Challenges in comparing 3D point clouds due to their unstructured nature and complex geometry.
method Information geometric framework for 3D point cloud shape analysis using Gaussian Mixture Models (GMMs) on a statistical manifold. Proposed MSKL divergence with upper and lower bounds.
result MSKL provides stable and monotonically varying values that directly reflect geometric variation, outperforming traditional distances and existing KL approximations.
We study the problem of finding strain-minimising stream surfaces in a divergence-free vector field. These surfaces are generated by motions of seed curves that propagate through the field in a strain minimising manner, i.e., they move without stretching or shrinking, preserving the length of their arbitrary arc. In ge…