New findings show sparse signals in MRA model require fewer measurements than previously thought.
problem Learning an unknown signal from repeated noisy images under group actions.
method Enhanced probabilistic method and analysis of uniform uncertainty principles.
result Sparse signals exhibit intermediate σ4 sample complexity, improving over traditional σ2. The study establishes uncertainty principles on harmonic manifolds of rank one.
problem Developing uncertainty principles for harmonic manifolds of rank one.
method Derivation of various uncertainty principles including Heisenberg, Morgen, Schrödinger, and Hömanders principles.
result Generalization of Hausdorff-Young inequality to harmonic manifolds of rank one.
New method improves uncertainty calibration in deep learning.
problem Systematic overconfidence in EDL on out-of-distribution inputs.
method Density-Informed Pseudo-count EDL (DIP-EDL) separates class prediction from uncertainty.
result DIP-EDL achieves asymptotic concentration and enhances robustness and uncertainty calibration.
We show that a well known uncertainty principle for functions on the circle can be derived from an uncertainty principle for the Euclidean motion group.
VCL adds uncertainty to contrastive learning models.
problem Lack of uncertainty quantification in contrastive learning methods.
method VCL uses a decoder-free framework that maximizes ELBO with InfoNCE loss and KL divergence.
result VCL provides meaningful uncertainty estimates and matches deterministic baselines in accuracy.
New framework improves model reliability under distribution shifts.
problem Lack of formal guarantees connecting shift magnitude to prediction reliability in TTA methods.
method Develops a PAC-Bayesian framework interpreting MMD-balls as credal sets.
result Establishes generalization bounds and provides epistemic uncertainty quantification.
A new method to break down insurance costs into risk and uncertainty.
problem Understanding and quantifying insurance costs in uncertain environments.
method An axiomatic approach to decompose premium principles into risk and deviation measures.
result Maximal risk and minimal deviation measures can be uniquely identified in decompositions.
Extends fractional Lp uncertainty principles with extremizers and stability results.
problem Investigating uncertainty principles in fractional Lp settings. method Analyzing the fractional Schrödinger equation to find extremal functions and sharp constants.
result Proves stability of extremizers for fractional uncertainty inequalities.
The paper proves uncertainty principles on Finsler measure spaces.
problem Uncertainty principles on Finsler measure spaces.
method Analyzes Lp-uncertainty principles on Finsler measure spaces with bounded curvatures. result Sharp Lp-uncertainty principles are proven and characterized. For unbounded operators A,B and C in general, with C closure of [A,B] does not lead to the uncertainty relation ||Au|| ||Bu|| >= |<C u,u> |/2. If A,B and C are part of the generators of a unitary representation of a Lie group then the uncertainty principle above holds.
Uncertainty principles such as Heisenberg's provide limits on the time-frequency concentration of a signal, and constitute an important theoretical tool for designing and evaluating linear signal transforms. Generalizations of such principles to the graph setting can inform dictionary design for graph signals, lead to …
The paper introduces a new discretization of Gaussian curvature on surfaces.
problem Discretizing Gaussian curvature on surfaces with conic singularities.
method Discrete conformal theory and variational principles with constraints.
result Established a discrete uniformization theorem for surfaces with non-positive Euler number.
Uniform bounds derived for fully non-linear equations.
problem Bounding fully non-linear equations uniformly in background metrics.
method Auxiliary Monge-Ampère equations and entropy-like quantities.
result Uniform L∞ bounds for systems coupling fully non-linear equations to their linearizations. Bayesian method detects outliers and uncertain points in data.
problem Detecting outliers and uncertain points in data using Bayesian methods.
method Generative model of data curation for aleatoric uncertainty, combining with epistemic uncertainty and outlier exposure.
result Principled Bayesian approach outperforms methods using aleatoric or epistemic uncertainty alone.
ProbFM provides principled uncertainty quantification for financial forecasting.
problem Lack of principled uncertainty quantification in financial applications.
method Probabilistic Time Series Foundation Model with Uncertainty Decomposition using Deep Evidential Regression (DER).
result DER maintains competitive forecasting accuracy while providing explicit epistemic-aleatoric uncertainty decomposition.
New proof of Kähler-Einstein Fano manifold L∞ estimates.
problem Uniform L∞ estimates for Kähler-Ricci flow on Kähler-Einstein Fano manifolds. method Using Chen-Cheng's auxiliary Monge-Ampère equation and the Alexandrov-Bakelman-Pucci maximum principle, without pluripotential theory.
result Uniform L∞ estimates derived for Kähler-Ricci flow on Kähler-Einstein Fano manifolds. We prove rigidity theorems for shrinking gradient Ricci solitons supporting the Heisenberg-Pauli-Weyl uncertainty principle with the sharp constant in Rn. In addtion, we partially give analogous rigidity results of the Caffarelli-Kohn-Nirenberg inequalities on shrinking Ricci solitons.
The paper proves how Transformers learn from context and generalize well.
problem Understanding how Transformers generalize from diverse tasks.
method Developed a statistical theory for in-context learning, separating risk into Bayes Gap and Posterior Variance.
result The Posterior Variance is task-independent, and the Bayes Gap decreases with more in-context examples.
Bayesian framework improves LLM evaluation stability and transparency.
problem Pass@k and avg@N are unstable and misleading for LLMs.
method Bayesian evaluation with posterior estimates and credible intervals.
result Posterior-based evaluation yields stable and transparent rankings.
This work tackles uncertainty quantification in language models, proposing a principled approach.
problem Challenges in identifying task-specific uncertainties in large language models.
method Bayesian decision theory, focusing on a similarity measure between generated and hypothetical true responses.
result Derives a measure for epistemic uncertainty based on a missing data perspective.
Investigates principles of generalization in list learning, refutes sample compression conjecture.
problem Determining applicability of classical principles in list PAC learning.
method Examines uniform convergence and sample compression in list PAC learning.
result Sample compression fails in list PAC learning, refutes conjecture.
New method improves active statistical inference by reducing noise.
problem Inaccurate uncertainty estimates in active sampling lead to noisy results.
method Robust sampling strategies that interpolate between uniform and active sampling based on uncertainty scores.
result The robust sampling ensures that the estimator is never worse than uniform sampling and usually outperforms active inference.
Gradient estimate proved for Donaldson's equation on Kähler manifolds.
problem Proving gradient estimates for Donaldson's equation on compact Kähler manifolds.
method Using uniform upper bounds for trωχφ and Alexandrov-Bakelman-Pucci (ABP) maximum principle. result Gradient estimate for Donaldson's equation derived from uniform bounds.
A new uncertainty principle helps traders better understand market activity.
problem Understanding high-frequency market activity and correlation.
method Integrates market activity, order-flow overlap, and response time into a clock-dependent uncertainty principle.
result Six rules of thumb for traders operating at market-making frequencies.
Alternative proofs for various inequalities on Riemannian manifolds.
problem Various functional inequalities on Riemannian manifolds.
method Generic functional inequality, Riccati pairs, solving Riccati-type ODE.
result Alternative proofs for multiple inequalities, including Hardy-type and Caccioppoli inequalities.
A novel Laplace-approximated Bayesian Tensor Network Kernel Machine (LA-TNKM) provides principled uncertainty estimates.
problem How to provide principled uncertainty estimates for tensor network kernel machines.
method Employing a linearized Laplace approximation for Bayesian inference.
result Consistently matches or surpasses Gaussian Processes and BNNs across diverse UCI regression benchmarks.
Sharp uncertainty principle for nodal sets in singular spaces.
problem Estimating the size of nodal sets in non-smooth spaces.
method Uncertainty principle applied to eigenfunctions in metric measure spaces with synthetic Ricci curvature bounds.
result New lower bounds on nodal set sizes in non-smooth spaces.
We give a maximum principle proof of interior derivative estimates for the Kähler-Ricci flow, assuming local uniform bounds on the metric.
Let H denote the standard one-point completion of a real Hilbert space. Given any non-trivial proper sub-set U of H one may define the so-called `Apollonian' metric d_U on U. When U \subset V \subset H are nested proper subsets we show that their associated Apollonian metrics satisfy the following uniform contraction p…
SNGP improves DNNs' uncertainty estimation with minimal changes.
problem Uncertainty estimation in deep learning models for real-time applications.
method Formalizing uncertainty as a minimax problem, SNGP adds weight normalization and replaces the output layer with a Gaussian process.
result SNGP outperforms other single-model approaches in uncertainty estimation across vision and language tasks.
This work provides uncertainty intervals for semantic latent variables in disentangled latent spaces.
problem Challenges in providing meaningful uncertainty quantification for semantic information in disentangled latent spaces.
method Uses quantile regression to output heuristic uncertainty intervals, calibrates these intervals to contain true latent values, and propagates them through the generator.
result Reliably communicates semantically meaningful, principled, and instance-adaptive uncertainty in image super-resolution and image completion.
New bounds for kernel regression under non-Gaussian noise.
problem Uncertainty quantification for function estimates from noisy observations.
method Novel non-asymptotic probabilistic uniform error bounds for kernel-based regression.
result Proposed bounds apply to a broad class of non-Gaussian noise distributions.
New uncertainty principle for Schrödinger equations on hyperbolic manifolds.
problem Uncertainty principle for Schrödinger equations on hyperbolic manifolds.
method General strategy of Escauriaza-Kenig-Ponce-Vega, new Carleman estimates, logarithmic convexity, new mollifier and weight function.
result Similar rigidity phenomenon as in Euclidean space persists in hyperbolic geometry.
Uniform estimates for complex equations on compact manifolds found.
problem Uniform estimates for (n−1)−form fully nonlinear PDEs on compact Hermitian manifolds. method Local comparison with Monge-Ampère equations and finding an appropriate elliptic operator.
result A priori L∞ estimate for the equations. Bayesian Scattering offers a simple baseline for image data uncertainty.
problem Lack of interpretable, mathematically grounded uncertainty quantification methods for image data.
method Coupling wavelet scattering transform with a simple probabilistic head.
result Bayesian Scattering provides sensible uncertainty estimates under distribution shifts.
We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop. It regularises the weights by minimising a compression cost, known as the variational free energy or the expected lower bound on the ma…
Assuming local uniform bounds on the metric for a solution of the Chern-Ricci flow, we establish local Calabi and curvature estimates using the maximum principle.
The paper examines optimal insurance design using Lambda-Value-at-Risk.
problem Optimal insurance design based on Lambda-Value-at-Risk.
method Analyzes optimal insurance solutions using Lambda-Value-at-Risk and closed-form expressions.
result Truncated stop-loss indemnity is optimal under certain conditions.
Bayesian principles improve neural additive models for better feature selection and uncertainty.
problem Lack of calibrated uncertainties and feature selection in neural additive models.
method Augmenting NAMs with Bayesian principles to provide credible intervals, feature selection, and interaction ranking.
result Improved performance on tabular datasets and real-world medical tasks.
Unified framework for planning under uncertainty using variational inference.
problem Planning under uncertainty with separate objectives for exploration and exploitation.
method Variational inference on a generative model augmented with priors.
result EFE-based planning emerges as variational inference, enabling scalable, resource-aware policies.
The paper shows how uncertainty quantification improves counterfactual explainability in AI.
problem Lack of foundational concepts in transparency research.
method Integrates uncertainty quantification into counterfactual explainability.
result Demonstrates competitive performance of an uncertainty-based explainer.
New rigorous uncertainty bounds for Gaussian Process regression.
problem Need for frequentist uncertainty bounds in applications like learning-based control.
method Introduce new uncertainty bounds that are rigorous and practically useful.
result New bounds are less conservative and more useful for practical applications.
We provide a constructive, variational proof of Rivin's realization theorem for ideal hyperbolic polyhedra with prescribed intrinsic metric, which is equivalent to a discrete uniformization theorem for spheres. The same variational method is also used to prove a discrete uniformization theorem of Gu et al. and a corres…
In an evolutionary system in which the rules of mutation are local in nature, the number of possible outcomes after m mutations is an exponential function of m but with a rate that depends only on the set of rules and not the size of the original object. We apply this principle to find a uniform upper bound for the…
Unified taxonomy for ML uncertainty in physics, validated.
problem Uncertainty quantification in machine learning for physics.
method Unified taxonomy, principled validation tools.
result Illustrated validation tools with examples.
In this paper we investigate a utility maximization problem with drift uncertainty in a multivariate continuous-time Black-Scholes type financial market which may be incomplete. We impose a constraint on the admissible strategies that prevents a pure bond investment and we include uncertainty by means of ellipsoidal un…
PAGER detects failures in deep regression models using a new framework.
problem Detecting failures in deep regression models.
method PAGER uses a combination of epistemic uncertainty and manifold non-conformity scores.
result PAGER accurately characterizes and detects failures in deep regressors.
Unified geometric approach to quantum indeterminacy.
problem Quantum indeterminacy and uncertainty principles.
method Geometric formulation using convex geometry and symplectic topology.
result Robertson-Schrodinger inequalities emerge as geometric principles.