Deep Gaussian Processes with polynomial kernels can collapse rapidly without proper hyperparameter tuning.
problem The collapse of Deep Gaussian Processes with polynomial kernels without careful hyperparameter tuning.
method Analysis using the Berry-Esseen Theorem and observation of prior behavior.
result The prior of a Deep Gaussian Process collapses rapidly towards zero or places negligible mass on low norm functions without proper hyperparameter tuning.
New bounds for SGD in high dimensions improve inference efficiency.
problem Quantifying uncertainty in high-dimensional SGD.
method Established non-asymptotic Berry--Esseen bounds for online least-squares SGD.
result Gaussian Central Limit Theorem holds for t ≳ d 1 + δ t \gtrsim d^{1+δ} t ≳ d 1 + δ , extending dimensional scaling. Study on volumes of random inscribed polytopes in projective geometries.
problem Estimating volumes of random inscribed polytopes in projective geometries.
method Central limit theorems and normal approximation for volumes and dual volumes of random inscribed polytopes.
result Established central limit theorems and normal approximation for volumes and dual volumes of random inscribed polytopes.
New statistical test for change-point detection using relative entropy.
problem Offline change-point detection using divergence metrics.
method Study of empirical relative entropy distributions, derivation of approximations, introduction of new Berry-Esseen bounds.
result Theoretical and practical validation of relative entropy for change-point detection.
Paper stabilizes bandit learning with regularization, improving inference under adaptive sampling.
problem Challenges in statistical inference with adaptive sampling.
method Refined stability condition for online algorithms, using regularized stochastic-mirror-descent-style methods.
result Derives precise regret bounds and asymptotic normality, showing necessity of regularization for valid inference.
Paper improves confidence intervals for LSA with multiplier bootstrap.
problem Improving confidence intervals for parameter estimation in LSA.
method Berry-Esseen bound for multivariate normal approximation and multiplier bootstrap.
result Valid confidence intervals for parameter estimation in LSA.
Mondrian random forests improve statistical inference for regression.
problem Improving statistical inference for regression functions.
method Combining bias and variance characterizations with debiasing and variance estimation.
result Valid statistical inference methods for unknown regression functions with error bounds.
Paper improves CLT and bootstrap approximations for LSA with decreasing step size.
problem Improving normal approximation and bootstrap methods for LSA with decreasing step sizes.
method Refined Berry-Esseen bounds and multiplier bootstrap procedure for LSA.
result Approximation rates up to 1 / n 1/\sqrt{n} 1/ n for LSA rescaled error distribution. Paper develops efficient incomplete U-statistics for degenerate cases.
problem High computational cost and non-standard asymptotic behavior in degenerate U-statistics.
method Characterizes dependence structure using hypergraph theory and combinatorial designs, bypassing traditional Hoeffding decomposition.
result Derives a Berry-Esseen bound for incomplete U-statistics of deterministic designs, enabling Gaussian limiting distributions in degenerate cases.
Paper derives convergence rates and confidence intervals for LSA with Markovian noise.
problem Analyzing convergence rates and constructing confidence intervals for LSA with Markovian noise.
method Derives non-asymptotic Berry-Esseen bounds and multiplier block bootstrap procedure.
result Provides O ( n − 1 / 4 ) \mathcal{O}(n^{-1/4}) O ( n − 1/4 ) convergence rates and guarantees consistent inference. The paper provides Gaussian approximations for decentralized Federated Learning.
problem Lack of asymptotic statistical guarantees for local SGD in Federated Learning.
method Two generalized Gaussian approximation results for local SGD trajectories.
result Valid multiplier bootstrap procedures and Gaussian bootstrap-based tests for detecting adversarial attacks.
Kernel smoothing on unknown manifolds with bounds and asymptotic normality.
problem Data on unknown manifolds without boundaries.
method Finite sample bounds and asymptotic normality for kernel smoothing and its derivatives.
result Established finite sample bounds and asymptotic normality for kernel smoothing.
We give a comprehensive theoretical characterization of a nonparametric estimator for the L 2 2 L_2^2 L 2 2 divergence between two continuous distributions. We first bound the rate of convergence of our estimator, showing that it is n \sqrt{n} n -consistent provided the densities are sufficiently smooth. In this smooth regime, we t…
Paper develops robust methods for large-scale testing without tuning parameters.
problem Heavy-tailed data in high-dimensional settings.
method Revisits Hodges-Lehmann estimator for robust inference without tuning parameters.
result Develops confidence intervals and controls false discovery proportion.
Study on financial systems using perturbed unimodal maps with heteroscedastic noise.
problem Analyzing systemic risk in financial systems using mathematical models.
method Investigation of one-dimensional unimodal maps perturbed by heteroscedastic noise, proving stability, convergence, and Lyapunov exponent continuity.
result Continuous dependence of average Lyapunov exponent on Markov chain parameters, and Gumbel's law for extreme values.
The paper provides rigorous guarantees for m-out-of-n bootstrap estimators of sample quantiles.
problem Lack of parameter-free guarantees for robust inference with heavy-tailed data.
method Central limit theorem and Edgeworth expansion for m-out-of-n bootstrap estimators of sample quantiles.
result Established rigorous guarantees for the soundness of m-out-of-n bootstrap estimators of sample quantiles.
Motivated by modern applications in which one constructs graphical models based on a very large number of features, this paper introduces a new class of cluster-based graphical models, in which variable clustering is applied as an initial step for reducing the dimension of the feature space. We employ model assisted cl…
Random forests remain among the most popular off-the-shelf supervised learning algorithms. Despite their well-documented empirical success, however, until recently, few theoretical results were available to describe their performance and behavior. In this work we push beyond recent work on consistency and asymptotic no…
We consider the problem of providing nonparametric confidence guarantees for undirected graphs under weak assumptions. In particular, we do not assume sparsity, incoherence or Normality. We allow the dimension D D D to increase with the sample size n n n . First, we prove lower bounds that show that if we want accurate infe…
Novel bounds improve TD learning consistency in RL.
problem Analyzing Temporal Difference learning's performance.
method High-dimensional concentration inequalities and Berry-Esseen bounds for Markov chain induced martingales.
result Sharp high-probability consistency guarantee for TD learning, matching asymptotic variance up to logarithmic factors.
Paper develops Gaussian approximations and bootstrap for federated LSA with trade-off bounds.
problem Analyzing convergence rates and trade-offs in federated linear stochastic approximation.
method Established Berry-Esseen-type bounds for federated LSA, developed multiplier bootstrap for inference.
result First federated Gaussian approximations with explicit trade-off terms and non-asymptotic validity guarantees.
Cheap methods improve uncertainty in SGD solutions.
problem Uncertainty quantification in SGD solutions.
method Two resampling-based methods: parallel resampling with replacement and online resampling.
result Significantly reduced computation effort in constructing confidence intervals.
This paper improves reinforcement learning by estimating return distributions using quantiles.
problem Improving reinforcement learning by estimating return distributions.
method Quantile-based distributional reinforcement learning, using quantile-projected distributional Bellman equations.
result The quantile-based approach achieves optimal sample efficiency and asymptotic efficiency.
This paper improves reinforcement learning by estimating return distributions using quantiles.
problem Improving reinforcement learning by estimating return distributions.
method The paper uses quantile-based distributional reinforcement learning to characterize return distributions.
result The quantile-based approach achieves optimal sample efficiency and asymptotic efficiency.
New statistical methods improve TD learning for policy evaluation.
problem Improving statistical inference for reinforcement learning.
method Polyak-Ruppert averaging, refined high-dimensional Berry-Esseen bounds, online plug-in estimator, asymptotic covariance matrix.
result Guaranteed finite-sample coverage of confidence regions and simultaneous confidence intervals.
We present a generic compact computational framework relying on structured random matrices that can be applied to speed up several machine learning algorithms with almost no loss of accuracy. The applications include new fast LSH-based algorithms, efficient kernel computations via random feature maps, convex optimizati…
The paper improves conformal prediction by analyzing the beta law of conditional coverage.
problem Improving finite-sample marginal coverage guarantees for non-i.i.d. data.
method The method uses Wasserstein distances to quantify deviations from the beta law of conditional coverage.
result The framework provides direct bounds on marginal coverage gaps and bad-calibration probabilities.
This work studies the smooth 1-Wasserstein distance and its limit distribution in high dimensions.
problem Addressing the curse of dimensionality in empirical approximation.
method Conducts a statistical study including limit distribution, bootstrap consistency, and concentration inequalities.
result Derives a nondegenerate limit distribution for empirical SWD, contrasting with classic W 1 W_1 W 1 . Paper provides Edgeworth expansions for network moments, improving accuracy of sampling distributions.
problem Accurate descriptions of sampling distributions of network moment statistics.
method Edgeworth expansion applied to studentized network moment statistics.
result Higher-order accurate approximation to sampling CDF of network moment statistics.
AI generates theorems and proofs for training theorem provers.
problem Limited human-written theorems and proofs for supervised learning.
method Proposes a neural generator to automatically synthesize theorems and proofs.
result Synthetic data improves automated theorem proving in Metamath.
Global inverse function theorem proved easily using Riemannian geometry.
problem Global inverse function theorem in Riemannian geometry.
method Hopf--Rinow theorem in Riemannian geometry.
result Hadamard's global inverse function theorem is proven easily.
A new comparison theorem for geometric spaces.
problem Geometric space comparison theorems.
method Relative form of Toponogov comparison theorem.
result New geometric space comparison theorem established.
Paper develops formulas and theorems in Hermitian geometry.
problem None explicitly stated in the abstract.
method Develops second variational formulas and index forms in Hermitian geometry.
result Establishes results analogous to classical theorems in Riemannian geometry.
The paper proves three circles theorems and Liouville type theorems for subharmonic and holomorphic functions.
problem Establishing theorems for subharmonic and holomorphic functions on specific geometric structures.
method Using subharmonic and holomorphic functions on Riemannian manifolds and gradient shrinking Ricci solitons.
result Proves Liouville type theorems as applications of the established theorems.
Revises a theorem by Thurston, finding a counter-example and a weaker version.
problem The bounded image theorem in Haken manifolds.
method Providing a counter-example and a weaker version of the second statement of Thurston's theorem.
result A counter-example and a weaker version of the second statement of Thurston's theorem are presented.
Proofs for Moon's theorem and its generalization.
problem Proving Moon's theorem and its generalization.
method Proofs based on key lemmas.
result Generalization of the four-vertex theorem.
Analyzes Saito vanishing theorem using L 2 L^{2} L 2 methods.
problem Proving the Saito vanishing theorem.
method Uses L 2 L^{2} L 2 -methods to prove the theorem. result Analytic proof of the Saito vanishing theorem.
Investigates proving geometric theorems over complex and real numbers using tilings.
problem Proving incidence theorems over C and R using the master theorem.
method Formalizes tiling proofs and introduces a hierarchy of theorems based on topological spaces.
result Identifies which theorems can or cannot be proved over C and R.
Extends symplectic reduction and theorem to Lie algebroids.
problem Symplectic reduction and theorem for Lie algebroids.
method Extends Marsden-Weinstein reduction and Darboux-Moser-Weinstein theorems.
result Obtained coisotropic embedding theorem for symplectic Lie algebroids.
Paper generalizes complex Brunn-Minkowski theory and proves new extension theorems.
problem Complex Brunn-Minkowski theory and extension theorems.
method Hilbert bundle approach to complex Brunn-Minkowski theory.
result Generalizes Guan's sharp strong openness theorem and sharp Ohsawa-Takegoshi extension theorem.
Proves Thurston's bounded image theorem for Haken manifolds.
problem Proving Thurston's bounded image theorem for Haken manifolds.
method Using recent developments in Kleinian group theory.
result A proof of Thurston's original bounded image theorem.
Method upgrades limit theorems to mixing limit theorems for dynamical systems.
problem Improving limit theorems for dynamical systems.
method General method for upgrading limit theorems to mixing limit theorems.
result Mixing limit theorems for specific subbundles of the Kontsevich-Zorich cocycle.
Formulates Index III lemma and Rauch III theorem with applications.
problem Develops new mathematical theorems based on existing ones.
method Formulation of Index III lemma and Rauch III theorem based on Index I, II lemmas and Rauch I, II theorems.
result Presented Rauch's type theorem and volume comparison result as applications.
In LM, we proved a family version of the famous Witten rigidity theorems and several family vanishing theorems for elliptic genera. In this paper, we gerenalize our theorems LM in two directions. First we establish a family rigidity theorem for the Dirac operator on loop space twisted by general positive energy loop gr…
The paper explains the topological origin of the distinction between incidence theorems over division rings and fields.
problem Understanding the distinction between incidence theorems over division rings and fields.
method Extending the surface-graph approach to noncommutative settings, the paper analyzes the topological properties of graphs embedded on surfaces of different genera.
result Theorems associated with graphs on the sphere hold over any division ring, while those on surfaces of positive genus typically hold only if the ground ring is a field.
Proves two theorems on odd-dimensional manifolds with boundary.
problem Proving theorems on manifolds with boundaries.
method Proof of theorems using mathematical techniques.
result Proved the general Kastler-Kalau-Walze and Dabrowski-Sitarz-Zalecki type theorems.
Sharp convergence theorem for sphere submanifolds proved.
problem Sphere submanifolds in spheres.
method Proved a sharp convergence theorem.
result New differentiable sphere theorem for submanifolds in spheres.
INT benchmark tests theorem proving agents' ability to generalize to unseen theorems.
problem Evaluating theorem proving agents' ability to generalize to unseen theorems.
method INT benchmark based on a theorem generation and proof procedure with adjustable knobs for measuring 6 types of generalization.
result MCTS can help agents prove new theorems.