pith. sign in

archive

Every paper Pith has read. Search by title, abstract, or pith.

2685 papers in stat.ML · page 15

  1. cs.LG 2026-05-01 reviewed
    Spectral sparsifiers keep GNN embedding geometry stable

    Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks

    Sanjukta Krishnagopal

  2. cs.LG 2026-05-01 reviewed
    TopoNTK detects topology that graph kernels miss

    Topological Neural Tangent Kernel

    Sanjukta Krishnagopal

  3. cs.LG 2026-05-01 reviewed
    Diffusion operator gives closed-form affinities for neural layers

    Diffusion Operator Geometry of Feedforward Representations

    Kanishka Reddy

  4. stat.ME 2026-05-01 reviewed
    Virtual particles enable MLE for mean-field limits from one trajectory

    Recursive Maximum Likelihood Estimation for Interacting Particle Systems using Virtual Particles

    Louis Sharrock +2

  5. cs.LG 2026-05-01 reviewed
    Disease perturbs biomarker modes for precise prognosis

    Disease Is a Spectral Perturbation

    John D. Mayfield +1

  6. cs.AI 2026-05-01 reviewed
    Agentic AI orchestration should be Bayesian

    Position: agentic AI orchestration should be Bayes-consistent

    Theodore Papamarkou +29

  7. math.OC 2026-05-01 reviewed
    Randomized subspaces accelerate Nesterov gradient methods

    Randomized Subspace Nesterov Accelerated Gradient

    Gaku Omiya +2

  8. cs.LG 2026-05-01 reviewed
    Volatility updates in HGF now avoid negative precision

    Robust volatility updates for Hierarchical Gaussian Filtering

    Christoph Mathys +4

  9. stat.ML 2026-05-01 reviewed
    Decentralized MCMC converges in Wasserstein distance for constrained distributions

    Decentralized Proximal Stochastic Gradient Langevin Dynamics

    Mohammad Rafiqul Islam +1

  10. stat.ML 2026-05-01 reviewed
    AI personas yield closed-form Bayesian updates for adaptive querying

    Adaptive Querying with AI Persona Priors

    Kaizheng Wang +2

  11. cs.LG 2026-05-01 reviewed
    Q-learning with multipattern approximation bounds regret at O(H² N^H √K)

    Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation

    Andrzej Ruszczynski +1

  12. stat.ML 2026-05-01 reviewed
    Regularized Newton boosting converges globally at O(1/k²)

    Gradient Regularized Newton Boosting Trees with Global Convergence

    Nikita Zozoulenko +3

  13. cs.LG 2026-05-01 reviewed
    Batch norm extended to complex domain neural networks

    Batch Normalization for Neural Networks on Complex Domains

    Xuan Son Nguyen +1

  14. stat.ME 2026-05-01 reviewed
    Predictive Bayesian credible sets can have near-zero coverage

    Concentration and Calibration in Predictive Bayesian Inference

    David T. Frazier +1

  15. cs.LG 2026-05-01 reviewed
    Spatial evidence gates Bayesian CP to fix coverage and bloat

    Optimal Spatio-Temporal Decoupling for Bayesian Conformal Prediction

    Yu-Hsueh Fang +1

  16. cs.LG 2026-05-01 reviewed
    M-CaStLe recovers causal structure in multivariate space-time grids

    M-CaStLe: Uncovering Local Causal Structures in Multivariate Space-Time Gridded Data

    J. Jake Nichol +4

  17. cs.LG 2026-05-01 reviewed
    Taylor mapping replaces kernel in point-set registration

    Structured Analytic Coherent Point Drift for Non-Rigid Point Set Registration

    Wei Feng +1

  18. cs.LG 2026-05-01 reviewed
    Analytic mappings shrink CPD deformation to order-dependent size

    Structured Analytic Coherent Point Drift for Non-Rigid Point Set Registration

    Wei Feng +1

  19. cs.LG 2026-05-01 reviewed
    Uniform penalty prevents RLVR collapse to few correct answers

    Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity

    Anamika Lochab +2

  20. cs.LG 2026-04-30 reviewed
    Gauge momentum stabilizes PDE parametrizations

    A Dirac-Frenkel-Onsager principle: Instantaneous residual minimization with gauge momentum for nonlinear parametrizations of PDE solutions

    Matteo Raviola +1

  21. stat.ML 2026-04-30 reviewed
    Constant informational speed lifts graph diffusion quality

    Information-geometric adaptive sampling for graph diffusion

    Yuhui Lu +2

  22. cs.LG 2026-04-30 reviewed
    Recursive partitioning enables linear-time Bayesian optimization

    Bayesian Optimization in Linear Time

    Jesse Schneider +1

  23. stat.ML 2026-04-30 reviewed
    Adjoint methods show finite gradient variance in diffusion fine-tuning

    A unified perspective on fine-tuning and sampling with diffusion and flow models

    Carles Domingo-Enrich +2

  24. cs.LG 2026-04-30 reviewed
    Soft segmentation learns decision weights with lowest regret

    OTSS: Output-Targeted Soft Segmentation for Contextual Decision-Weight Learning

    Renjun Hu +1

  25. stat.ML 2026-04-30 reviewed
    SHIFT cuts localized contamination RMSE for dose-response curves

    SHIFT: Robust Double Machine Learning for Average Dose-Response Functions under Heavy-Tailed Contamination

    Eichi Uehara

  26. stat.ML 2026-04-30 reviewed
    Covariance-aware penalties boost neural net accuracy on correlated inputs

    Adaptive Norm-Based Regularization for Neural Networks

    Muhammad Qasim +1

  27. cs.LG 2026-04-30 reviewed
    Wasserstein regret optimization yields exact water-filling policy

    Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback

    Yikai Wang +2

  28. cs.LG 2026-04-30 reviewed
    DRRO solves RLHF regret exactly via water-filling under l1 sets

    Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback

    Yikai Wang +2

  29. cs.LG 2026-04-30 reviewed
    Latent diffusion plus conformal bands tops load imputation benchmarks

    SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting

    Arnaud Zinflou

  30. quant-ph 2026-04-30 reviewed
    Matchgate evolutions yield provable quantum Gaussian processes

    Provable and scalable quantum Gaussian processes for quantum learning

    Jonas J\"ager +5

  31. eess.SP 2026-04-30 reviewed
    Sequential GPs enable streaming inference in signal processing

    Sequential Inference for Gaussian Processes: A Signal Processing Perspective

    Daniel Waxman +2

  32. cs.LG 2026-04-30 reviewed
    Kernel smoothing gives accurate value estimates for LLM reasoning

    Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning

    Shijin Gong +5

  33. cs.LG 2026-04-30 reviewed
    Kernel smoothing enables accurate LLM value estimates from few traces

    Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning

    Shijin Gong +5

  34. stat.ML 2026-04-30 reviewed
    Mixture of experts sharpens prediction-powered inference

    Prediction-powered Inference by Mixture of Experts

    Yanwu Gu +2

  35. math.ST 2026-04-30 reviewed
    Decoupled descent forces train error to match test error

    Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing

    Max Lovig

  36. cs.LG 2026-04-30 reviewed
    Smooth losses achieve linear consistency rates

    Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction

    Mehryar Mohri +1

  37. cs.LG 2026-04-30 reviewed
    Standard DPO losses are inconsistent for neural networks

    Mind the Gap: Structure-Aware Consistency in Preference Learning

    Mehryar Mohri +1

  38. cs.LG 2026-04-30 reviewed
    MILD algorithm corrects deferral bias caused by imbalanced experts

    Optimized Deferral for Imbalanced Settings

    Corinna Cortes +3

  39. stat.CO 2026-04-30 reviewed
    R packages unify forecast reconciliation across three frameworks

    FoReco and FoRecoML: A Unified Toolbox for Forecast Reconciliation in R

    Daniele Girolimetto +3

  40. math.ST 2026-04-30 reviewed
    Bayesian one-pass algorithm attains optimal posterior convergence

    Bayesian online learning in the one-pass regime: Frequentist validity and uncertainty quantification

    Jeyong Lee +3

  41. stat.ML 2026-04-30 reviewed
    Bayesian X-learner recovers calibrated CATE posteriors under heavy tails

    Bayesian X-Learner: Calibrated Posterior Inference for Heterogeneous Treatment Effects under Heavy-Tailed Outcomes

    Eichi Uehara

  42. stat.ML 2026-04-30 reviewed
    Tree discretization plus ILP matching cuts bias in causal estimates

    A Novel Computational Framework for Causal Inference: Tree-Based Discretization with ILP-Based Matching

    Tianyu Yang +1

  43. stat.ML 2026-04-30 reviewed
    Trees plus ILP cut bias and time in causal matching

    A Novel Computational Framework for Causal Inference: Tree-Based Discretization with ILP-Based Matching

    Tianyu Yang +1

  44. cs.LG 2026-04-29 reviewed
    Copula transform lifts ensemble to 0.96 accuracy on groundwater pollution

    Smart Ensemble Learning Framework for Predicting Groundwater Heavy Metal Pollution

    T. Ansah-Narh +8

  45. stat.ME 2026-04-29 reviewed
    Neural network picks regression variables using OLS estimates

    Linear Models, Variable Selection, Artificial Intelligence

    By Riyadh Alrawkan +3

  46. cs.LG 2026-04-29 reviewed
    νGPT transfers learning rates across width and depth

    Learning Rate Transfer in Normalized Transformers

    Boris Shigida +2

  47. cs.LG 2026-04-29 reviewed
    HyCNNs approximate quadratics with exponentially fewer parameters

    Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport

    Shayan Hundrieser +2

  48. cs.LG 2026-04-29 reviewed
    Prior change removes ln ln T from Squint bound

    A Note on How to Remove the $\ln\ln T$ Term from the Squint Bound

    Francesco Orabona

  49. cs.LG 2026-04-29 reviewed
    Revenue learners converge for any distribution but at arbitrarily slow rates

    On the Learning Curves of Revenue Maximization

    Steve Hanneke +3

  50. math.PR 2026-04-29 reviewed
    Transformers converge to noise-synchronized particle systems

    Stochastic Scaling Limits and Synchronization by Noise in Deep Transformer Models

    Andrea Agazzi +4