The paper emphasizes the importance of value distribution in reinforcement learning.
problem The focus on value expectation in reinforcement learning is insufficient.
method Developed a new algorithm based on the distributional perspective of reinforcement learning.
result Demonstrated significant distributional instability in reinforcement learning control.
New perspective on distribution shift helps make learning easier.
problem Learning with different training and target distributions.
method Formalizing and exploring Positive Distribution Shift (PDS).
result Distribution shift can be positive, making learning easier.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
problem Understanding latent concept encodings in AI models.
method Probabilistic perspective on CAVs, deriving mean and covariance.
result CAVs can be adversarially manipulated, highlighting a vulnerability.
Bayesian deep learning improves neural network accuracy and generalization.
problem Improving accuracy and calibration of deep neural networks.
method Bayesian marginalization and deep ensembles to approximate marginalization, and tempering for calibrating predictive distributions.
result Bayesian approaches improve deep neural networks' accuracy and generalization.
Defines a similarity measure for classification distributions.
problem Measuring similarity between classification distributions.
method Proposes task similarity, a novel measure quantifying performance of source distributions on target distributions.
result Empirical task similarity correlates with transfer efficiency and semantic similarity of source distributions.
A new method for calculating ES from VaR under Solvency II.
problem The need for a more appropriate risk measure (ES) than VaR.
method Developed PELVE method for multiple insurers, analyzing existence, uniqueness, and expressions for different payoff distributions.
result The choice of method is crucial when payoffs are from different distribution families.
A new CoVaR framework integrates expert views using entropy pooling.
problem Risk assessment and spillover effects from diverse expert views.
method Entropy pooling method to integrate expert views and compute general CoVaR.
result General CoVaR shows linear relationships with expectations and differences in expectations, and nonlinear dependencies with variance, quantiles, and correlation.
In this article we present an alternative model for the distribution of household incomes in the United States. We provide arguments from two differing perspectives which both yield the proposed income distribution curve, and then fit this curve to empirical data on household income distribution obtained from the Unite…
Novel algorithms for entropic optimal transport from an optimisation perspective.
problem Solving the entropic-regularised optimal transport problem.
method Developed novel methods inspired by mirror descent, solving semi-dual problems or non-convex constrained problems over joint distributions.
result Non-asymptotic rates of convergence for the proposed methods under minimal assumptions.
Paper examines Gaussian process perspective of CNNs.
problem Understanding when and why CNNs perform well.
method Casts CNNs in a Gaussian process framework.
result Gains insights into CNN performance and assumptions.
This work analyzes IRM and ERM from sample complexity perspective, revealing different behaviors under various distribution shifts.
problem Choosing between IRM and ERM for OOD generalization.
method Sample complexity analysis comparing IRM and ERM under different data generation mechanisms.
result IRM is preferred over ERM for certain distribution shifts, leading to better OOD generalization.
Paper proposes bypassing implicit assumption in GM-based AD methods.
problem Lack of anomalous data and implicit assumption in GM-based AD methods.
method Integrating Discriminative idea to GMM for AD tasks (DiGMM).
result Establishes a connection between generative and discriminative models for AD.
The paper introduces a DRM for causal inference, offering a flexible method to analyze counterfactual distributions.
problem Estimating mean causal effects is limited; a distributional perspective is needed for a more thorough understanding.
method The paper employs a semiparametric density ratio model (DRM) with an empirical likelihood (EL) approach to estimate counterfactual distribution functions.
result The DRM framework enables direct and transparent causal inference from a distributional perspective, validated by numerical studies.
New perspective on federated learning as posterior inference, improving optimization.
problem Optimizing global models in distributed learning settings.
method Formulated as posterior inference problem, using MCMC for approximate inference and federated averaging for refinement.
result Federated posterior averaging (FedPA) outperforms existing methods on benchmarks.
Classifies multiply-transitive (2,3,5)-distributions using modern Cartan geometry.
problem Classifying multiply-transitive (2,3,5)-distributions. method Modern Cartan-geometric approach, incorporating G2 structure theory. result Complete classifications in both complex and real settings, with full curvature and infinitesimal holonomy.
New findings clarify the link between distributional closeness and representational similarity.
problem When and why do different neural network representations become similar?
method Identifiability theory, focusing on model families including autoregressive language models.
result Small Kullback-Leibler divergence does not guarantee similar representations.
The thesis presents a new perspective on high-dimensional optimization.
problem The failure point of classical optimization methods in high dimensions.
method A distributional view of optimization, focusing on random objective functions and Bayesian Optimization.
result The distributional view explains predictable progress in high-dimensional optimization and provides insights into optimal step size control.
Survey of recent methods for testing high-dimensional multinomial hypotheses.
problem Statistical power issues in high-dimensional multinomial testing.
method Review of recent methods focusing on asymptotic normality and minimax perspectives.
result Refined tests can have high power even when null distributions are non-normal.
Proposes a probabilistic method for generating semantically-aware adversarial examples.
problem Generating adversarial examples that are difficult for humans to detect while preserving semantics.
method Embeds subjective understanding of semantics as a distribution into adversarial example generation.
result Achieves higher success rates in circumventing adversarial defense mechanisms.
This paper examines federated learning from an information-theoretic perspective.
problem Understanding the conditions under which averaging model parameters in federated learning is beneficial.
method Measuring mutual information between representations and inputs/labels in local models and comparing it to the averaged model.
result Empirical results confirm the practical usefulness of averaging for neural networks, even with varying local dataset distributions.
Unified framework for distributed compressed SGD under (L0,L1)-smoothness.
problem Understanding the joint effect of batch noise, adaptivity, and compression in distributed stochastic optimization.
method Developed a unified theoretical framework using SDEs that incorporate curvature-dependent terms.
result Normalizing updates in DCSGD stabilizes convergence, with normalization degree determined by noise structure and landscape regularity.
Empirical Bayes rates via variational approximations and prior decomposition.
problem Nonparametric and high-dimensional inference convergence rates.
method Variational perspective and prior decomposition.
result Empirical Bayes posterior rates derived from variational Bayes.
Studies report that firms do not invest in cost-effective green technologies. While economic barriers can explain parts of the gap, behavioural aspects cause further under-valuation. This could be partly due to systematic deviations of decision-making agents' perceptions from normative benchmarks, and partly due to the…
Two derivations of PCA for distributional data.
problem PCA for datasets of distributions.
method Two derivations: variance maximization and reconstruction error minimization.
result Closed-form solution for distributional PCA.
Unified framework for training diffusion and flow models to sample from target distributions.
problem Training diffusion and flow models to sample from target distributions defined by exponential tilting.
method Unified framework combining stochastic optimal control and non-equilibrium thermodynamics perspectives.
result Unified bias-variance decompositions and theoretical support for adjoint-based methods.
Normalizing flows simplify complex distributions through bijective transformations.
problem Defining expressive probability distributions efficiently.
method Bijective transformations on a base distribution.
result Unified perspective on normalizing flows for modeling and inference.
Generative AI can solve in-context learning problems using a martingale perspective.
problem Estimating when a conditional generative model can solve an in-context learning problem.
method Bayesian interpretation, ancestral sampling, generative predictive p-value.
result Developed a method to assess the suitability of CGMs for ICL problems using generative predictive p-values.
Empirical comparison of PCA and ICA on noisy time series.
problem Comparing PCA and ICA performance on noisy data.
method Applied PCA and ICA to two simulated noisy time series with varying distribution parameters and noise levels.
result ICA outperforms PCA due to considering higher moments of data distribution.
Neural networks' weights don't converge to stationary points but training loss stabilizes.
problem The disconnect between theoretical analyses and neural network training practice.
method An invariant measure perspective inspired by ergodic theory of dynamical systems.
result The distribution of weights converges to an approximate invariant measure, explaining loss stabilization.
Stochastic Gradient Descent with a constant learning rate (constant SGD) simulates a Markov chain with a stationary distribution. With this perspective, we derive several new results. (1) We show that constant SGD can be used as an approximate Bayesian posterior inference algorithm. Specifically, we show how to adjust …
Gradient clipping helps private SGD converge despite potential bias.
problem Gradient clipping in private SGD can bias convergence.
method Theoretical analysis and empirical evaluation of gradient clipping effects.
result Gradient clipping can prevent convergence to stationary points and introduces bias.
New method detects uncertainty in neural networks for out-of-distribution detection.
problem Detecting out-of-distribution inputs to ensure model reliability.
method Predictive topological uncertainty (pTU) based on persistent homology.
result pTU provides a statistical framework for OOD detection.
A class of conserved models of wealth distributions are studied where wealth (or money) is assumed to be exchanged between a pair of agents in a population like the elastically colliding molecules of a gas exchanging energy. All sorts of distributions from exponential (Boltzmann-Gibbs) to something like Gamma distribut…
New framework improves adversarial robustness certification for various perturbations.
problem Certifying robustness against adversarial attacks in deep learning models.
method Unified functional optimization approach with non-Gaussian smoothing noise for multiple types of attacks.
result Achieves better certification results and identifies key trade-offs between accuracy and robustness.
Monge-Kantorovich distances, otherwise known as Wasserstein distances, have received a growing attention in statistics and machine learning as a powerful discrepancy measure for probability distributions. In this paper, we focus on forecasting a Gaussian process indexed by probability distributions. For this, we provid…
A new Bayesian perspective on counterfactual explanations improves model interpretability.
problem Improving interpretability of machine learning models through counterfactual explanations.
method Introducing a generalized Bayes perspective on counterfactual explanations, using a Gibbs posterior and distance-based priors.
result Counterfactual explanations are mathematically equivalent to the MAP estimate within the generalized Bayes framework.
We examine the efficiency of the Asymmetric Power ARCH (APARCH) model in the case where the residuals follow the standardized Pearson type IV distribution. The model is tested with a variety of loss functions and the efficiency is examined via application of several statistical tests and risk measures. The results indi…
We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target risk where the distributions' divergence---expressed as a ratio---controls the tra…
We align distributional data using regularized Wasserstein means.
problem Aligning distributional data from different domains.
method Regularized Wasserstein means with variational transportation.
result Sparse representation captures desired properties and reduces mapping cost.
We present a new algorithm for approximate inference in probabilistic programs, based on a stochastic gradient for variational programs. This method is efficient without restrictions on the probabilistic program; it is particularly practical for distributions which are not analytically tractable, including highly struc…
New analysis shows scores learn data manifolds better than distributions.
problem Learning the full distribution vs. just the data manifold.
method Novel analysis of scores in the small-σ regime.
result Scores learn data manifold information Θ(σ−2) stronger than distribution information. Offline RL with pre-trained features amplifies errors even under mild shifts.
problem Sample-efficient offline RL with pre-trained features under mild distribution shift.
method Empirical study of offline RL with pre-trained neural representations.
result Substantial error amplification occurs even with pre-trained features, requiring stronger conditions for successful offline RL.
Analyzes neural networks using spectral perspectives.
problem Understanding neural network initialization and training.
method Examines the Conjugate Kernel and Neural Tangent Kernel spectra.
result Lends insights into neural network initialization and training properties.
Unified view on learning unnormalized distributions using NCE.
problem Learning unnormalized distributions across different communities.
method Noise-Contrastive Estimation (NCE) for a unified perspective.
result Established finite-sample convergence rates for exponential families.
Medix uses the median to detect outliers from unlabeled data for robust OOD detection.
problem Challenges in using unlabeled data for OOD detection due to mixed InD and OOD samples.
method Introduces Medix, a framework using the median operation to identify outliers from unlabeled data.
result Empirical results show Medix outperforms existing methods in open-world settings.
A new perspective on self-attention models using MLPs.
problem Improving sequence modeling with self-attention mechanisms.
method Introducing HyperMLP and HyperGLU, which use dynamic two-layer MLPs with reverse-offset layout.
result HyperMLP/HyperGLU consistently outperform softmax-attention baselines.
Study identifies cancer genes through graph anomaly analysis of protein interactions.
problem Insufficient modeling of biological information in protein interaction networks for cancer gene identification.
method Proposes HIerarchical-Perspective Graph Neural Network (HIPGNN) to detect weight heterogeneity and spectral flattening in cancer gene nodes.
result HIPGNN detects weight heterogeneity and spectral flattening, leading to improved cancer gene identification.
Abstract perspective on quadratic programming for optimal portfolio allocation.
problem Optimal allocation problems in long portfolio theory.
method Using maximum principles and distinguished boundaries in reproducing kernel Hilbert spaces.
result Support of an optimal distribution lies in a variety intersecting a distinguished boundary.