Study proposes a new method to estimate bias-correction term for ATE estimation.
problem Estimating the bias-correction term for ATE estimation.
method Directly estimating the bias-correction term by minimizing Bregman divergence.
result Automatic covariate balancing property achieved through specific model choices.
New optimization method corrects data-driven optimizer's curse.
problem Over-optimistic evaluation in data-driven optimization.
method Smoothed f-Divergence Distributionally Robust Optimization (DRO). result Statistical bound on out-of-sample performance nearly tightest.
Proposes a guaranteed regularization method for maximum likelihood estimation using gauge symmetry in Kullback-Leibler divergence.
problem Overfitting in maximum likelihood estimation.
method Introduces a regularization approach based on gauge symmetry in Kullback-Leibler divergence.
result The method provides a theoretically guaranteed optimal model without frequent hyperparameter tuning.
Jeffreys Flow improves robustness of Boltzmann generators for rare event sampling.
problem Rare events and metastable trapping in sampling physical systems with rough energy landscapes.
method Introduces Jeffreys Flow, a robust generative framework using Parallel Tempering distillation and symmetric Jeffreys divergence to mitigate mode collapse and improve mode coverage.
result Minimizing Jeffreys divergence suppresses mode collapse and corrects inaccuracies in multi-modal distributions.
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.
Introduces TDRC to balance TD's ease and soundness.
problem TD learning's instability and divergence issues.
method Gradient Temporal-Difference Learning with Regularized Corrections (TDRC).
result TDRC performs as well as TD when TD works, but is sound in divergent cases.
New method improves data efficiency in reinforcement learning by composing skills.
problem Improving data efficiency in reinforcement learning by composing previously mastered skills.
method Extending policy improvement to maximum entropy framework, introducing successor features, and explicitly learning divergence between base policies.
result Proposes a novel approach that outperforms or matches existing methods in various tasks.
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.
In this letter, we generalize the convolutional NMF by taking the β-divergence as the contrast function and present the correct multiplicative updates for its factors in closed form. The new updates unify the β-NMF and the convolutional NMF. We state why almost all of the existing updates are inexact and approximat…
A new method detects and corrects adversarial attacks on classifiers.
problem Detecting and correcting adversarial attacks on machine learning models.
method Unsupervised autoencoder trained with KL divergence loss to match predictions.
result Almost completely neutralizes powerful attacks on MNIST and Fashion-MNIST.
We consider nonparametric estimation of L2, Renyi-α and Tsallis-α divergences between continuous distributions. Our approach is to construct estimators for particular integral functionals of two densities and translate them into divergence estimators. For the integral functionals, our estimators are based on cor…
Paper extends 2D β-CNMF with exact multiplicative updates.
problem Improving nonnegative matrix factor deconvolution for 2D data.
method Derives exact multiplicative updates for β-CNMF factors. result The updates lead to monotonically decreasing β-divergence. We establish bounds on the KL divergence between two multivariate Gaussian distributions in terms of the Hamming distance between the edge sets of the corresponding graphical models. We show that the KL divergence is bounded below by a constant when the graphs differ by at least one edge; this is essentially the tighte…
SRFE clarifies KL divergences without unifying learning frameworks.
problem Inductive biases of KL divergences and their limitations.
method Introducing SRFE, a log-moment-based functional of the likelihood ratio.
result SRFE recovers KL divergences as limits and reveals a mean-variance tradeoff.
DM framework improves robustness and efficiency in latent-mixture models.
problem Efficient and robust inference in latent-mixture models.
method Divergence-minimization framework with monotonic convergence and robustness guarantees.
result DM yields consistent and asymptotically normal estimators under correct specification.
New methods minimize GFlowNet training divergences for better sampling.
problem Training GFlowNets with KL divergence leads to biased and high-variance estimators.
method Design and implement efficient estimators for four divergence measures.
result Properly minimizing these divergences yields a provably correct and effective training scheme.
A new model corrects inhomogeneity in Optimal Transport with Boundary.
problem Inhomogeneity in UROT models for Optimal Transport with Boundary.
method Proposed a modified entropic regularization term to make UROT models homogeneous.
result Homogeneous UROT model preserves properties of standard UROT while correcting inhomogeneity.
In the existing financial literature, entropy based ideas have been proposed in portfolio optimization, in model calibration for options pricing as well as in ascertaining a pricing measure in incomplete markets. The abstracted problem corresponds to finding a probability measure that minimizes the relative entropy (al…
Proposes a method to prevent overfitting in deep DRE models.
problem Overfitting in deep DRE models using empirical Bregman divergence.
method Introduces a non-negative correction for empirical Bregman divergence.
result The proposed method mitigates train-loss hacking and improves performance.
Conditional forecasts improve performative prediction accuracy.
problem Performative predictions undermine standard forecasting methods.
method Condition forecasts on covariates to make them forecast-invariant.
result Proper scoring rules fail under conditioning, but two solutions are identified.
A new method Expectigrad improves on Adam and RMSProp by reducing divergence and improving performance.
problem Improving the convergence properties of adaptive gradient methods like Adam and RMSProp.
method Adjusts stepsizes using a per-component unweighted mean of all historical gradients and a bias-corrected momentum term.
result Cannot diverge on convex optimization problems that cause Adam to diverge.
A new framework for offline RL improves policy flexibility and regularity.
problem Lack of environmental interactions in offline RL leads to poor policy performance.
method Proposes a behavior-regularized implicit policy framework with modified policy-matching methods.
result The framework improves policy effectiveness and robustness beyond static datasets.
The paper analyzes MACD using operator theory.
problem Understanding the mathematical foundation of MACD.
method Developed a functional-analytic framework interpreting MACD as a phase-corrected, smoothed derivative operator.
result MACD is structurally equivalent to a band-pass filter and can be expressed as a finite difference of delayed and doubly averaged signals.
Improved analysis of Langevin diffusion discretization without convexity assumptions.
problem Improving sampling and learning algorithms for Langevin diffusion.
method Improved Euler-Maruyama discretization with polynomial time dependence and smoothness assumption.
result Achieves O(η2) rate in KL divergence, matching numerical SDEs. In the context of machine learning, disparate impact refers to a form of systematic discrimination whereby the output distribution of a model depends on the value of a sensitive attribute (e.g., race or gender). In this paper, we propose an information-theoretic framework to analyze the disparate impact of a binary cla…
Paper improves variational inference by tightening bounds using perturbation theory.
problem Improving variational inference's bias and KL divergence approximation.
method Revisits perturbation theory to derive corrections that tighten variational bounds.
result New bounds are tighter and more mass-covering, leading to higher likelihoods.
Improved BAI under DP reduces gap to constant.
problem Fixed-confidence BAI under global DP for Bernoulli distributions.
method New lower bound, stopping rule, and Top Two sampling rule.
result Reduces gap to a small multiplicative constant.
A novel stepwise VI method using vine copulas for complex latent dependence.
problem Modeling complex latent dependence structures in probabilistic models.
method Stepwise estimation of vine copula parameters using Rényi divergence and a stopping criterion.
result Our method outperforms mean-field VI and is more parsimonious in complex applications.
Study finds the minimum number of finite Gaussian mixtures for best approximation.
problem Finding the minimum number of finite Gaussian mixtures for best approximation.
method Local moment matching for upper bound and spectral analysis for lower bound.
result Corrects a previous lower bound in the case of Gaussian mixing distributions.
Dynamic Vocabulary Pruning stabilizes LLM training by removing low-probability tokens.
problem Training Large Language Models (LLMs) with Reinforcement Learning (RL) causes numerical divergence between inference and training.
method Dynamic Vocabulary Pruning (DVP) constrains the RL objective to a safe vocabulary that excludes low-probability tokens.
result DVP stabilizes training by reducing systematic bias introduced by the extreme tail of the token distribution.
Improved variational inference for geophysical inverse problems with data correction.
problem High computational cost and accuracy issues in Bayesian inference for geophysical inverse problems.
method Amortized variational inference with latent distribution correction using physics-based priors.
result Improved robustness of amortized variational inference under data distribution shifts.
FSGLD improves federated data sampling by correcting noisy gradients.
problem Noisy gradients and delayed communication in federated data.
method Conductive gradients to correct noisy gradients in distributed SGLD.
result FSGLD converges to true posterior even with delayed communication.
New method learns models from data density and generates samples.
problem Learning models that estimate data density and generate samples.
method Denoising density estimators (DDEs) trained to minimize KL-divergence.
result Our method converges to correct solution without specific network architecture.
NeuTra-lizes bad geometry in HMC using neural transport.
problem Difficult-to-normalize posterior distributions with unfavorable geometry.
method Neural transport (NeuTra) HMC, using inverse autoregressive flows (IAF) to correct geometry.
result Significantly outperforms vanilla HMC in time and effective-sample-size rates.
Unified framework for estimating density ratios across multiple distributions.
problem Binary density ratio estimation for multiple distributions.
method Unified framework based on Bregman divergence minimization.
result Generalization of binary DRE methods to multiple distributions.
DSM on manifolds removes singularities and computes small-noise expansions.
problem DSM on manifolds with singular noise.
method Rao-Blackwellized score matching, nearest-point projection, intrinsic Riemannian score.
result Canonical target equals intrinsic Riemannian score up to a small correction.
GenDICE estimates stationary values from offline data.
problem Estimating stationary values from limited offline data.
method Ratio correction based on stationary distribution properties, variational divergence minimization.
result Consistent estimation of stationary values possible in offline settings.
We provide finite-sample analysis of a general framework for using k-nearest neighbor statistics to estimate functionals of a nonparametric continuous probability density, including entropies and divergences. Rather than plugging a consistent density estimate (which requires k→∞ as the sample size $n \to \in…
CD learning is shown to be an adversarial game for fitting models.
problem Difficulty in understanding the convergence properties of CD learning.
method Presented an alternative derivation of CD without approximation, showing it as a time-reversal adversarial game.
result CD is an adversarial learning procedure where a discriminator tries to classify time-reversed Markov chains.
SDG uses optimal control to improve classifier guidance in low-density regions.
problem Inefficient guidance in low-density regions of posterior distributions.
method Integrates stochastic optimal control with Stein variational inference to compute the steepest descent direction.
result SDG improves guidance in low-density regions, outperforming standard methods.
This paper presents a general iterative bias correction procedure for regression smoothers. This bias reduction schema is shown to correspond operationally to the L2 Boosting algorithm and provides a new statistical interpretation for L2 Boosting. We analyze the behavior of the Boosting algorithm applied to commo…
We introduce several techniques for sampling and visualizing the latent spaces of generative models. Replacing linear interpolation with spherical linear interpolation prevents diverging from a model's prior distribution and produces sharper samples. J-Diagrams and MINE grids are introduced as visualizations of manifol…
Producing overlapping schemes is a major issue in clustering. Recent proposed overlapping methods relies on the search of an optimal covering and are based on different metrics, such as Euclidean distance and I-Divergence, used to measure closeness between observations. In this paper, we propose the use of another meas…
Adaptive stepsizing improves sampling in Bayesian neural networks.
problem Scalable sampling of posterior distributions in Bayesian neural networks.
method SA-SGLD, employing time rescaling to adapt stepsize dynamically.
result SA-SGLD achieves more accurate posterior sampling than SGLD.
Training large machine learning (ML) models with many variables or parameters can take a long time if one employs sequential procedures even with stochastic updates. A natural solution is to turn to distributed computing on a cluster; however, naive, unstructured parallelization of ML algorithms does not usually lead t…
We develop a universal distributional calculus for regulated volumes of metrics that are singular along hypersurfaces. When the hypersurface is a conformal infinity we give simple integrated distribution expressions for the divergences and anomaly of the regulated volume functional valid for any choice of regulator. Fo…
Detects change points in time series focusing on specific components.
problem Identifying moments when specific components of multivariate time series change distributions.
method Two-stage non-parametric algorithm: causal structure learning followed by change point detection.
result Validated the approach on synthetic and real-world datasets.
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.