301 papers
This paper establishes the universality of high-dimensional spectral behavior and statistical limits for asymmetric rank-one spiked tensor models with non-Gaussian noise, demonstrating that the maximum-likelihood estimator's performance matches the Gaussian case under finite fourth-moment assumptions.
This paper formalizes the loss of diversity in classifier-free guidance as "generative distortion," characterizes its emergence via a high-dimensional phase transition using statistical physics, and proposes a novel guidance schedule with a negative-guidance window to mitigate variance shrinkage while preserving class separability.
This paper proposes Singular Bayesian Neural Networks, which parameterize weights as low-rank products to induce a singular posterior that captures structured correlations, thereby achieving competitive predictive performance and improved uncertainty calibration with significantly fewer parameters and tighter generalization bounds compared to standard mean-field approaches.
This paper presents a theoretical analysis establishing quantitative error bounds for Bayesian inverse problems using generative priors, demonstrating that the posterior error inherits the convergence rate of the prior in Wasserstein distance, and validates these findings through numerical experiments on benchmarks and an elliptic PDE inverse problem.
This paper proposes a control-variates-based transfer learning approach for scalar-on-function regression that utilizes dataset-specific summary statistics to preserve privacy, establishes a theoretical equivalence between offset and control-variates methods, and derives convergence rates that account for discretization errors and cross-dataset covariance similarities.
This paper proposes a few-shot image fusion framework that leverages a Granular Ball Pixel Computation algorithm to generate adaptive, confidence-aware incomplete priors, enabling a lightweight neural network to learn effective fusion rules from minimal data without requiring real fused images for supervision.
This paper provides a first-order analysis demonstrating that cross-entropy training in transformers induces a coupled specialization of attention routing and value updates—functioning as a two-timescale EM procedure—that sculpts low-dimensional Bayesian manifolds, thereby explaining how gradient-based optimization enables precise probabilistic reasoning.
This paper introduces computationally efficient and statistically consistent Random Forest variants that minimize the maximum risk across diverse environments to improve out-of-distribution generalization, offering novel guarantees for mean squared error, negative reward, and regret-based risks.
The paper introduces EarthquakeNPP, a rigorous benchmark for earthquake forecasting that reveals current Neural Point Process models fail to outperform the classical ETAS model, highlighting the need for improved collaboration between seismology and machine learning communities.
This paper proposes additive tree models for two-sample density ratio estimation using a novel balancing loss that enables efficient training via supervised learning algorithms and generalized Bayesian inference for uncertainty quantification, with demonstrated effectiveness in high-dimensional settings and generative model assessment.
This paper proposes a novel data-driven framework using offline reinforcement learning and survival analysis to estimate optimal pricing and inventory control policies in sequential environments with censored and dependent demand, overcoming challenges like missing profit information and non-stationarity by approximating the problem as a high-order Markov decision process.
This paper proposes a general family of statistical models for pairwise comparisons that relaxes the restrictive stochastic transitivity assumption by utilizing low-dimensional skew-symmetric matrices, thereby achieving minimax-rate optimality and superior predictive performance in complex, real-world scenarios where traditional models like Bradley-Terry fail.
The paper introduces CLIQUE, a novel model-agnostic method for calculating local variable importance that overcomes the limitations of existing techniques like LIME and SHAP by capturing locally dependent relationships and interaction behaviors while being directly applicable to multi-class classification problems.
This paper proposes a geometric memorization theory demonstrating that diffusion models transition from generalization to exact copying through a smooth, gradual collapse of latent dimensionality, where salient features and finer details progressively "freeze out" as data becomes scarce, mirroring physical systems condensing into low-energy configurations.
This paper proposes two robust criteria and a corresponding sampling-based difference-of-convex algorithm for learning optimal treatment rules that maximize truncated mean survival time and buffered survival probabilities in the presence of censored survival data, demonstrating superior performance through simulations and an AIDS clinical trial application.
This paper introduces a selective prediction framework for molecular structure retrieval from mass spectra that leverages retrieval-level uncertainty and distribution-free risk control to allow models to abstain from low-confidence predictions, thereby ensuring annotations meet specified error rate constraints in high-stakes applications.
This paper compares Monte Carlo Dropout and Conformal Prediction for uncertainty estimation in CNNs trained on Fashion-MNIST, revealing that while H-CNN VGG16 achieves higher accuracy, GoogLeNet offers better calibration and Conformal Prediction provides statistically guaranteed reliability for high-stakes applications.
This paper introduces Generalized Gaussian Mixture Processes (GGMPs), a scalable and tractable Gaussian process-based framework that enables multimodal conditional density estimation by combining local mixture fitting, cross-input component alignment, and per-component heteroscedastic GP training to overcome the unimodal limitations of standard GP regression.
This paper introduces PP-LUCB, a cost-efficient algorithm that optimally combines biased LLM-generated proxy scores with selective human audits to identify the best service system configuration while providing statistically valid confidence guarantees and significantly reducing audit costs.
This paper presents a unified Bayesian optimization framework using Gaussian processes with derivative observations and advanced extensions like Optimal Transport and random Fourier features to efficiently accelerate the search for minima and saddle points on potential energy surfaces, bridging theoretical formulation with practical implementation through accompanying Rust code.