New characterization limits sampling with inexact scores.
problem Limiting sampling with inexact scores for unbiased results.
method Characterized types of inexact score oracle access.
result Weaker error assumptions rule out tractability of unbiased sampling.
Proposes a new model for image restoration combining deep learning and total variation.
problem Restoring images from limited data with low-rank constraints insufficient.
method Regularized Deep Matrix Factorized (RDMF) model using deep neural network's low-rank bias and total variation.
result Outperforms state-of-the-art models in image restoration from few observations.
The paper connects neural collapse and low-rank bias in networks with L2 regularization.
problem Understanding the emergence of low-rank bias and neural collapse in L2-regularized networks.
method Unified theoretical framework linking TCV and rank of weight matrices, proving global optimality of DNC1, and establishing a benign landscape property.
result Zero TCV across intermediate layers minimizes representation cost under natural architectural constraints, and DNC1 is globally optimal.
This work shows how penalising bias terms in norm regularisation leads to sparse solutions.
problem Understanding the relation between parameter norm regularization and the sparsity of neural network solutions.
method Analyzes one hidden ReLU layer networks with unidimensional data, showing the norm required for function representation and the importance of the bias term's norm.
result Penalising the bias terms in regularisation leads to sparse solutions, enforcing the uniqueness and sparsity of the minimal norm interpolator.
We consider the problem of estimating the parameters of a d-dimensional rectified Gaussian distribution from i.i.d. samples. A rectified Gaussian distribution is defined by passing a standard Gaussian distribution through a one-layer ReLU neural network. We give a simple algorithm to estimate the parameters (i.e., th…
Geometric framework analyzes bias in variational inference for posterior functionals.
problem Analyzing the bias of posterior functionals under variational approximations.
method Developed a geometric framework to evaluate the bias of posterior functionals using the variational tangent space.
result The leading-order bias of a posterior functional is determined by its component orthogonal to the variational tangent space.
Ideas from the image processing literature have recently motivated a new set of clustering algorithms that rely on the concept of total variation. While these algorithms perform well for bi-partitioning tasks, their recursive extensions yield unimpressive results for multiclass clustering tasks. This paper presents a g…
The paper studies curves in Riemannian manifolds using total variation flow.
problem Analyzing the evolution of curves in Riemannian manifolds using total variation.
method Defining and proving the existence of strong solutions to the flow equations, showing variational equality, and proving convergence.
result Strong solutions converge to a constant map in finite time for non-positive sectional curvature.
Optimal pre-processing reduces disparate impact by minimizing total variation distance.
problem Achieving fairness in data outputs based on protected attributes.
method Using pre-processing to enforce fairness, minimizing total variation distance between pre-processed and original data distributions.
result The problem of fairness can be formulated as a linear program, efficiently solvable.
The paper analyzes the bias-variance tradeoff for Bregman divergences.
problem Understanding the bias-variance tradeoff for Bregman divergences.
method Analyzes the bias-variance tradeoff through operations in dual space.
result Derives several results including a generalized law of total variance and ensembling operations.
We reformulate the Cont-Bouchaud model of financial markets in terms of classical "super-spins" where the spin value is a measure of the number of individual traders represented by a portfolio manager of an investment agency. We then extend this simplified model by switching on interactions among the super-spins to mod…
We show a very simple and general total second variation formula for Perelman's W-functional at arbitrary points in the space of Riemannian metrics. Moreover we perform a study of the properties of the variations of Kähler structures. We deduce a quite simple and general total second variation formula for P…
A new metric MSD detects bias in datasets efficiently.
problem Detecting bias in AI systems and datasets.
method Introduced Maximum Subgroup Discrepancy (MSD) metric and a practical algorithm based on MIO.
result MSD provides a linear sample complexity for practical applications, distinguishing biases effectively.
In this note, we study the relationship between the variational gap and the variance of the (log) likelihood ratio. We show that the gap can be upper bounded by some form of dispersion measure of the likelihood ratio, which suggests the bias of variational inference can be reduced by making the distribution of the like…
We derive variational formulas for the total Q-prime curvature under the deformation of strictly pseudoconvex domains in a complex manifold. We also show that the total Q-prime curvature agrees with the renormalized volume of such domains with respect to the complete Einstein-Kähler metric. In the appendix, by Rod Gove…
New method improves sampling efficiency in complex stochastic systems.
problem Sampling efficiency in nonconvex stochastic gradient cases.
method Reflection coupling for unadjusted generalized Hamiltonian Monte Carlo.
result Quantitative Gaussian concentration bounds and convergence rates established.
Paper addresses Byzantine attacks in decentralized optimization over networks.
problem Byzantine attacks in decentralized stochastic optimization over static and time-varying networks.
method Formulate a TV norm-penalized approximation of the problem, solve using stochastic subgradient method.
result Proposed method reaches a neighborhood of the Byzantine-free optimal solution.
We consider the problem of estimating a function defined over n locations on a d-dimensional grid (having all side lengths equal to n1/d). When the function is constrained to have discrete total variation bounded by Cn, we derive the minimax optimal (squared) ℓ2 estimation error rate, parametrized by …
We analyze bias-variance of margin losses.
problem Understanding model overfitting/underfitting.
method Bias-variance decomposition for strictly convex margin losses.
result Expected risk decomposes into central model risk and data variation.
Estimates treatment effects in bipartite systems with partial eligibility and interference.
problem Randomized experiments in bipartite systems with partial treatment eligibility and interference.
method Formalizes eligibility-constrained bipartite experiments, defines PTTE and STTE, identifies conditions, develops ensemble estimators, introduces projection.
result Proposed estimators recover PTTE and STTE with low bias and variance, corrects interference bias in field experiments.
We study the theoretical properties of image denoising via total variation penalized least-squares. We define the total vatiation in terms of the two-dimensional total discrete derivative of the image and show that it gives rise to denoised images that are piecewise constant on rectangular sets. We prove that, if the t…
The paper uses a graph autoencoder to learn unbiased plant-pollinator interaction embeddings.
problem Sampling bias in citizen science data affects ecological network analysis.
method Bipartite graph variational autoencoder with HSIC for fairness.
result The method mitigates sampling bias and provides unbiased embeddings.
Paper proposes MMC to avoid high-density bias in clustering.
problem High-density bias in density-based clustering.
method Introduces mass distribution as a better foundation for clustering, proposing mass-maximization clustering (MMC).
result MMC avoids high-density bias and discovers clusters of arbitrary shapes, sizes, and densities.
The total variation distance is a core statistical distance between probability measures that satisfies the metric axioms, with value always falling in [0,1]. This distance plays a fundamental role in machine learning and signal processing: It is a member of the broader class of f-divergences, and it is related to …
Revisits VIC method to correct intrinsic reward bias in stochastic environments.
problem Intrinsic reward bias in VIC leading to suboptimal solutions.
method Proposes two methods based on transitional probability model and Gaussian mixture model to correct bias.
result Achieves maximal empowerment through corrected intrinsic reward.
Through the direct study of the analysis estimator we derive oracle inequalities with fast and slow rates by adapting the arguments involving projections by Dalalyan, Hebiri and Lederer (2017). We then extend the theory to the square root analysis estimator. Finally, we focus on (square root) total variation regularize…
Estimating and optimizing Mutual Information (MI) is core to many problems in machine learning; however, bounding MI in high dimensions is challenging. To establish tractable and scalable objectives, recent work has turned to variational bounds parameterized by neural networks, but the relationships and tradeoffs betwe…
SaR-SVM-STV improves hyperspectral image classification with shape-adaptive reconstruction and denoising.
problem Classifying hyperspectral images with limited labeled data.
method Shape-adaptive Reconstruction (SaR) for pixel preprocessing, SVM for probability estimation, and Smoothed Total Variation (STV) for denoising.
result SaR-SVM-STV outperforms SVM-STV with fewer labeled data.
Study variational properties of curves in half-plane with area constraints.
problem Characterize critical points of inverse mean curvature.
method Variational analysis of curves with boundary constraints.
result Existence and stability of critical points with prescribed area.
New method mitigates bias without sensitive data using causal graph and variational autoencoder.
problem Lack of fairness strategies when sensitive attributes are not collected.
method SRCVAE framework based on causal graph for inferring a proxy sensitive attribute.
result Significant improvements in fairness metrics over existing methods.
Study variations of Riemannian submersions to maintain geodesic fibers and positive curvatures.
problem Maintain geodesic fibers and positive sectional curvatures in Riemannian submersions.
method Vary Riemannian metrics while keeping fibers totally geodesic and horizontal distribution fixed.
result Conditions for making sectional curvatures positive and existence of fat submersions.
Bias correction needed after deep learning regression training.
problem Systematic error accumulation in deep learning regression models.
method Adjust bias of the machine learning model post-training.
result Bias correction efficiently solves error accumulation.
We examine the total mixed scalar curvature of a fixed distribution as a functional of a pseudo-Riemannian metric. We develop variational formulas for quantities of extrinsic geometry of the distribution to find the critical points of this action. Together with the arbitrary variations of the metric, we consider also v…
Estimates parameters of interconnected linear systems using total variation penalization.
problem Joint estimation of parameters in interconnected linear dynamical systems.
method Total variation penalized least-squares estimator.
result The MSE goes to zero as the number of systems increases, even with constant trajectory length.
The law of total probability may be deployed in binary classification exercises to estimate the unconditional class probabilities if the class proportions in the training set are not representative of the population class proportions. We argue that this is not a conceptually sound approach and suggest an alternative ba…
Sharp inequality between TV and Hellinger distances for Gaussian mixtures.
problem Understanding the relationship between total variation and Hellinger distances for Gaussian mixtures.
method Established a general upper bound on Hellinger distance in terms of TV distance raised to a power, demonstrating sharpness with specific examples.
result The Hellinger distance between two Gaussian mixtures is bounded by the TV distance raised to a power 1−o(1), where o(1) is of order 1/loglog(1/TV). VTD uses deep embeddings to estimate treatment effects from longitudinal data without unconfoundedness assumption.
problem Challenges in estimating individualized treatment effects from longitudinal observational data due to confounding bias.
method Leverages deep variational embeddings and observed proxies to learn hidden confounders.
result Effective in estimating treatment effects when hidden confounding is the leading bias.
Paper proposes a method to estimate total variation distance for synthetic data fidelity.
problem Assessing the fidelity of synthetic data generated by AI.
method Discriminative approach to estimate total variation distance between two distributions.
result Estimation of total variation distance reduces to quantifying Bayes risk in classification.
A bias classifier is introduced to resist adversarial attacks.
problem Resisting adversarial attacks on deep neural networks (DNNs).
method Introducing the bias part of a DNN with Relu as the activation function as a classifier, and adding a random first-degree part to make it information-theoretically safe.
result The bias classifier is more robust than DNNs of similar size against adversarial attacks.
Paper introduces a new method to model epidemic dynamics with varying parameters.
problem Capturing discontinuous variations in epidemic model parameters.
method Total variation regularization with Iterated Nelder--Mead optimization.
result The method accurately models epidemic dynamics with instant changes.
Ensembles improve classifier performance by reducing bias, not variance.
problem Improving classifier performance through ensemble methods.
method Extended bias-variance decomposition for classification tasks, introducing dual reparameterization.
result Ensembling reduces bias in classifiers, contrary to the traditional view.
We consider the problem of minimizing the sum of submodular set functions assuming minimization oracles of each summand function. Most existing approaches reformulate the problem as the convex minimization of the sum of the corresponding Lovász extensions and the squared Euclidean norm, leading to algorithms requiring …
Bounds on treatment effect sensitivity in causal reasoning using Hölder's inequality.
problem Estimating treatment effects in presence of unobserved confounders.
method Using Hölder's inequality, derived bounds on confounding bias based on unmeasured confounding strength.
result Bounds are tight under specific conditions of independence between U and T/Y.
Proximal algorithms applied to current deformation into cycles.
problem Deformation of de Rham currents into cycles.
method Proximal algorithms, total variation denoising for differential forms.
result Calibrated cycles constructed in calibrated manifolds.
Example shows learnable distributions not privately learnable.
problem Learnable distributions under non-private conditions not transferable to differential privacy.
method Example of a distribution class learnable up to constant error in total variation distance but not under differential privacy.
result Contradicts conjecture of Ashtiani on learnability under differential privacy.
Algorithm learns stochastic system dynamics from data.
problem Recovering interpretable symbolic expressions for stochastic systems.
method Data-driven, trajectory averaging, drift-informed correction.
result Recover coefficients and densities to within 5% and 0.01 in total variation, respectively.
New method for mesh denoising using TGV of normal vector field.
problem Improving mesh quality by removing noise.
method Proposes a novel TGV formulation for normal vector fields on triangular meshes.
result New method outperforms existing techniques in mesh denoising experiments.
Graphs with non-negative Ollivier-Ricci curvature cannot be expanders.
problem Understanding the relationship between graph curvature and expansion properties.
method Proving an inequality linking isoperimetric profiles to total variation decay of random walks.
result Graphs with non-negative Ollivier-Ricci curvature cannot be expanders.