Statistics, Machine Learning papers, 2025-05-01 to 2025-10-31

Papers

901. Singleton-Optimized Conformal Prediction2509.24095 · 28 Sept 2025
902. Sample-Efficient Optimisation over the Outputs of Generative Models2509.23800 · 28 Sept 2025
903. Symmetry-Aware Bayesian Optimization via Max Kernels2509.25051 · 29 Sept 2025
904. MAD: Manifold Attracted Diffusion2509.24710 · 29 Sept 2025
905. Quantitative convergence of trained single layer neural networks to Gaussian processes2509.24544 · 29 Sept 2025
906. When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis2509.24912 · 29 Sept 2025
907. Neural Optimal Transport Meets Multivariate Conformal Prediction2509.25444 · 29 Sept 2025
908. ActiveCQ: Active Estimation of Causal Quantities2509.24293 · 29 Sept 2025
909. Conservative Decisions with Risk Scores2509.25588 · 29 Sept 2025
910. A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems2509.24920 · 29 Sept 2025
911. Coupling Generative Modeling and an Autoencoder with the Causal Bridge2509.25599 · 29 Sept 2025
912. Fair Classification by Direct Intervention on Operating Characteristics2509.25481 · 29 Sept 2025
913. Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws2509.24914 · 29 Sept 2025
914. Preference-Based Dynamic Ranking Structure Recognition2509.24493 · 29 Sept 2025
915. PEARL: Performance-Enhanced Aggregated Representation Learning2509.24312 · 29 Sept 2025
916. One-shot Conditional Sampling: MMD meets Nearest Neighbors2509.25507 · 29 Sept 2025
917. On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms2509.25126 · 29 Sept 2025
918. Identifying All ε-Best Arms in (Misspecified) Linear Bandits2510.00073 · 29 Sept 2025
919. BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields2509.26005 · 30 Sept 2025
920. When Langevin Monte Carlo Meets Randomization: New Sampling Algorithms with Non-asymptotic Error Bounds beyond Log-Concavity and Gradient Lipschitzness2509.25630 · 30 Sept 2025
921. Pretrain-Test Task Alignment Governs Generalization in In-Context Learning2509.26551 · 30 Sept 2025
922. Private Learning of Littlestone Classes, Revisited2510.00076 · 30 Sept 2025
923. An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes2509.26429 · 30 Sept 2025
924. Spectral gap of Metropolis-within-Gibbs under log-concavity2509.26175 · 30 Sept 2025
925. Estimating Dimensionality of Neural Representations from Finite Samples2509.26560 · 30 Sept 2025
926. Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?2509.26149 · 30 Sept 2025
927. Test time training enhances in-context learning of nonlinear functions2509.25741 · 30 Sept 2025
928. Sharpness of Minima in Deep Matrix Factorization2509.25783 · 30 Sept 2025
929. Graph Distribution-valued Signals: A Wasserstein Space Perspective2509.25802 · 30 Sept 2025
930. Approximation of differential entropy in Bayesian optimal experimental design2510.00734 · 1 Oct 2025
931. On the Adversarial Robustness of Learning-based Conformal Novelty Detection2510.00463 · 1 Oct 2025
932. Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting2510.01414 · 1 Oct 2025
933. A universal compression theory for lottery ticket hypothesis and neural scaling laws2510.00504 · 1 Oct 2025
934. Guaranteed Noisy CP Tensor Recovery via Riemannian Optimization on the Segre Manifold2510.00569 · 1 Oct 2025
935. Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time2510.01098 · 1 Oct 2025
936. Optimal placement of wind farms via quantile constraint learning2510.01093 · 1 Oct 2025
937. CINDES: Classification induced neural density estimator and simulator2510.00367 · 1 Oct 2025
938. Bayesian Neural Networks for Functional ANOVA model2510.00545 · 1 Oct 2025
939. Private Realizable-to-Agnostic Transformation with Near-Optimal Sample Complexity2510.01291 · 1 Oct 2025
940. Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling2510.01329 · 1 Oct 2025
941. Deep Hedging Under Non-Convexity: Limitations and a Case for AlphaZero2510.01874 · 2 Oct 2025
942. Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory2510.01930 · 2 Oct 2025
943. Adaptive Kernel Selection for Stein Variational Gradient Descent2510.02067 · 2 Oct 2025
944. Higher-arity PAC learning, VC dimension and packing lemma2510.02420 · 2 Oct 2025
945. Predictive inference for time series: why is split conformal effective despite temporal dependence?2510.02471 · 2 Oct 2025
946. Uniform-in-time convergence bounds for Persistent Contrastive Divergence Algorithms2510.01944 · 2 Oct 2025
947. A reproducible comparative study of categorical kernels for Gaussian process regression, with new clustering-based nested kernels2510.01840 · 2 Oct 2025
948. Hybrid Physics-ML Framework for Pan-Arctic Permafrost Infrastructure Risk at Record 2.9-Million Observation Scale2510.02189 · 2 Oct 2025
949. Beyond Linear Diffusions: Improved Representations for Rare Conditional Generative Modeling2510.02499 · 2 Oct 2025
950. Learning Multi-Index Models with Hyper-Kernel Ridge Regression2510.02532 · 2 Oct 2025
951. Non-Asymptotic Analysis of Data Augmentation for Precision Matrix Estimation2510.02119 · 2 Oct 2025
952. AI Foundation Model for Time Series with Innovations Representation2510.01560 · 2 Oct 2025
953. Adaptive randomized pivoting and volume sampling2510.02513 · 2 Oct 2025
954. Neural Jump ODEs as Generative Models2510.02757 · 3 Oct 2025
955. Spectral Thresholds for Identifiability and Stability:Finite-Sample Phase Transitions in High-Dimensional Learning2510.03809 · 4 Oct 2025
956. Self-Speculative Masked Diffusions2510.03929 · 4 Oct 2025
957. Transformed $\ell_1$ Regularizations for Robust Principal Component Analysis: Toward a Fine-Grained Understanding2510.03624 · 4 Oct 2025
958. The analogy theorem in Hoare logic2510.03685 · 4 Oct 2025
959. Simulation-based inference via telescoping ratio estimation for trawl processes2510.04042 · 5 Oct 2025
960. Scalable Causal Discovery from Recursive Nonlinear Data via Truncated Basis Function Scores and Tests2510.04276 · 5 Oct 2025
961. Adaptive Coverage Policies in Conformal Prediction2510.04318 · 5 Oct 2025
962. Relative Information Gain and Gaussian Process Regression2510.04277 · 5 Oct 2025
963. Minima and Critical Points of the Bethe Free Energy Are Invariant Under Deformation Retractions of Factor Graphs2510.05380 · 6 Oct 2025
964. Fisher-Bingham-like normalizing flows on the sphere2510.04762 · 6 Oct 2025
965. Causal Abstractions, Categorically Unified2510.05033 · 6 Oct 2025
966. Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation2510.04602 · 6 Oct 2025
967. Divergence Phase Index: A Riesz-Transform Framework for Multidimensional Phase Difference Analysis2510.04426 · 6 Oct 2025
968. Model Monitoring: A General Framework with an Application to Non-life Insurance Pricing2510.04556 · 6 Oct 2025
969. Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling2510.04406 · 6 Oct 2025
970. Kernel ridge regression under power-law data: spectrum and generalization2510.04780 · 6 Oct 2025
971. Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning2510.04970 · 6 Oct 2025
972. Curiosity-Driven Development of Action and Language in Robots Through Self-Exploration2510.05013 · 6 Oct 2025
973. Refereed Learning2510.05440 · 6 Oct 2025
974. A Noise Resilient Approach for Robust Hurst Exponent Estimation2510.04811 · 6 Oct 2025
975. Learning Survival Models with Right-Censored Reporting Delays2510.04421 · 6 Oct 2025
976. Set to Be Fair: Demographic Parity Constraints for Set-Valued Classification2510.04926 · 6 Oct 2025
977. A Probabilistic Basis for Low-Rank Matrix Learning2510.05447 · 6 Oct 2025
978. Bilevel optimization for learning hyperparameters: Application to solving PDEs and inverse problems with Gaussian processes2510.05568 · 7 Oct 2025
979. Implicit Updates for Average-Reward Temporal Difference Learning2510.06149 · 7 Oct 2025
980. On the Theory of Continual Learning with Gradient Descent for Neural Networks2510.05573 · 7 Oct 2025
981. A General Constructive Upper Bound on Shallow Neural Nets Complexity2510.06372 · 7 Oct 2025
982. Domain-Shift-Aware Conformal Prediction for Large Language Models2510.05566 · 7 Oct 2025
983. Online Matching via Reinforcement Learning: An Expert Policy Orchestration Strategy2510.06515 · 7 Oct 2025
984. Root Cause Analysis of Outliers in Unknown Cyclic Graphs2510.06995 · 8 Oct 2025
985. Fourier Analysis on the Boolean Hypercube via Hoeffding Functional Decomposition2510.07088 · 8 Oct 2025
986. PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing2510.06935 · 8 Oct 2025
987. Bayesian Nonparametric Dynamical Clustering of Time Series2510.06919 · 8 Oct 2025
988. Split Conformal Classification with Unsupervised Calibration2510.07185 · 8 Oct 2025
989. Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death2510.07501 · 8 Oct 2025
990. Q-Learning with Fine-Grained Gap-Dependent Regret2510.06647 · 8 Oct 2025
991. Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix2510.06685 · 8 Oct 2025
992. Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarios2510.07099 · 8 Oct 2025
993. From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation2510.07624 · 8 Oct 2025
994. PAC Learnability in the Presence of Performativity2510.08335 · 9 Oct 2025
995. Permutation-Invariant Spectral Learning via Dyson Diffusion2510.08535 · 9 Oct 2025
996. Calibrating Decision Robustness via Inverse Conformal Risk Control2510.07750 · 9 Oct 2025
997. On the Optimality of Tracking Fisher Information in Adaptive Testing with Stochastic Binary Responses2510.07862 · 9 Oct 2025
998. A Honest Cross-Validation Estimator for Prediction Performance2510.07649 · 9 Oct 2025
999. Surrogate Graph Partitioning for Spatial Prediction2510.07832 · 9 Oct 2025
1000. Accumulated Aggregated D-Optimal Designs for Estimating Main Effects in Black-Box Models2510.08465 · 9 Oct 2025