pith. sign in

archive

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

2684 papers in stat.ML · page 9

  1. math.NA 2026-05-10 reviewed
    Fast sketching accelerates power method for low-rank approximations

    Accelerating Power Method with Fast Sketching for Stronger Low-Rank Approximation

    Shabarish Chenakkod +1

  2. econ.EM 2026-05-10 reviewed
    Hybrid booster adds linear terms to trees for macro forecasts

    LGB+: A Macroeconomic Forecasting Road Test

    Philippe Goulet Coulombe

  3. stat.ML 2026-05-10 reviewed
    Normalizing flows recover fast equilibrium from slow data alone

    Learning stochastic multiscale models through normalizing flows

    Anan Saha +1

  4. econ.EM 2026-05-10 reviewed
    Risk-adjusted metrics favor professional forecasters

    Quantifying the Risk-Return Tradeoff in Forecasting

    Philippe Goulet Coulombe

  5. stat.ML 2026-05-10 reviewed
    Metropolis-Hastings steps fix discretization bias in diffusion correctors

    Metropolis-Adjusted Diffusion Models

    Kevin H. Lam +5

  6. math.ST 2026-05-10 reviewed
    Matching bounds set exact mu threshold for submatrix detection

    Minimax optimal submatrix detection: Sharp non-asymptotic rates

    Parker Knight +1

  7. math.ST 2026-05-10 reviewed
    Exact signal thresholds derived for submatrix detection

    Minimax optimal submatrix detection: Sharp non-asymptotic rates

    Parker Knight +1

  8. math.OC 2026-05-10 reviewed
    Power law model splits Muon and SignSGD into three phases

    Phases of Muon: When Muon Eclipses SignSGD

    Elliot Paquette +5

  9. cs.LG 2026-05-10 reviewed
    History-space neural operator halves rollout error for memory PDEs

    HS-FNO: History-Space Fourier Neural Operator for Non-Markovian Partial Differential Equations

    Lennon J. Shikhman

  10. cs.LG 2026-05-10 reviewed
    History-aware operator halves rollout error for memory PDEs

    HS-FNO: History-Space Fourier Neural Operator for Non-Markovian Partial Differential Equations

    Lennon J. Shikhman

  11. stat.ML 2026-05-10 reviewed
  12. cs.LG 2026-05-10 reviewed
    Dataset pairs 1700 vision-model embeddings with training metadata

    SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations

    Mario Edoardo Pandolfo +6

  13. stat.ME 2026-05-10 reviewed
  14. stat.ML 2026-05-10 reviewed
    Mean-field SVGD converges in L2 at explicit polynomial rates

    Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow

    L\'ena\"ic Chizat +3

  15. stat.ML 2026-05-10 reviewed
    Single-index bandits admit optimal regret of order T to the two-thirds

    Optimal Regret for Single Index Bandits

    Devdan Dey +2

  16. cs.LG 2026-05-10 reviewed
    Inputs recovered to match any target output distribution

    Inverse Design for Conditional Distribution Matching

    Ori Meidler +2

  17. cs.LG 2026-05-10 reviewed
    Gravity decoder lifts link prediction in directed graphs

    GravityGraphSAGE: Link Prediction in Directed Attributed Graphs

    Riccardo Porcedda +3

  18. cs.IT 2026-05-10 reviewed
    Feature selection tolerates noise and weak symmetry

    Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions

    Dier Tang (1) +4

  19. stat.ME 2026-05-10 reviewed
    Shared parametric value function scales RL measurement to large tasks

    Reinforcement Learning Measurement Model

    Wenqian Xu +1

  20. cs.LG 2026-05-10 reviewed
    Permutation routing across model copies improves generalization

    Improving Generalization by Permutation Routing Across Model Copies

    Shuhei Kashiwamura +1

  21. cs.LG 2026-05-10 reviewed
    Optimal coefficient stabilizes MeanFlow training

    On Variance Reduction in Learning Mean Flows

    Juanwu Lu +1

  22. cs.CV 2026-05-10 reviewed
    Geometry-aware VAE outperforms baselines on skeleton trajectories

    An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectories

    Arafat Rahman +3

  23. cs.CV 2026-05-10 reviewed
    Shape geometry VAE outperforms standard models on skeleton sequences

    An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectories

    Arafat Rahman +3

  24. cs.CV 2026-05-10 reviewed
    Elastic shape VAE beats standard models on skeletal trajectories

    An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectories

    Arafat Rahman +3

  25. cs.LG 2026-05-09 reviewed
    Forward KL regularization yields first fast rates for offline contextual bandits

    Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability

    Qingyue Zhao +3

  26. stat.ME 2026-05-09 reviewed
    Unsigned CATE estimates power randomization tests without splitting data

    Fit CATE Once: Model-Assisted Randomization Tests Without Sample Splitting

    Fangnan Zheng +1

  27. stat.ML 2026-05-09 reviewed
    Sub-network Laplace approximations underestimate predictive variance

    Optimality of Sub-network Laplace Approximations: New Results and Methods

    Swarnali Raha +2

  28. cs.LG 2026-05-09 reviewed
    Muon fails to converge on convex Lipschitz functions

    Muon Does Not Converge on Convex Lipschitz Functions

    Tetiana Parshakova +4

  29. stat.ML 2026-05-09 reviewed
    Nine-step guideline corrects bias in ML on health surveys

    Survey-aware Machine Learning: A Guideline for Valid Population Health Inference based on Scoping Review

    YongKyung Oh +3

  30. cs.LG 2026-05-09 reviewed
    Popular Wikipedia pages show weaker periodicity than rare ones

    TailedTS: Benchmark Dataset for Heavy-Tailed Time Series Prediction and Periodicity Quantification

    Xinyu Chen +3

  31. math.OC 2026-05-09 reviewed
    Soft penalties make stochastic paths match observed marginals

    Learning Generative Dynamics with Soft Law Constraints: A McKean-Vlasov FBSDE Approach

    Samer El Boustany +4

  32. cs.LG 2026-05-09 reviewed
    Co-distillation lifts small-model math accuracy by 6 points over GRPO

    CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization

    Soo Min Kwon +4

  33. math.OC 2026-05-09 reviewed
    Variance reduction shortens time complexity in parallel optimization

    Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction

    Zhirayr Tovmasyan +2

  34. stat.ML 2026-05-09 reviewed
    Noiseless inverse optimization has tight O(d/T) generalization

    Tight Generalization Bounds for Noiseless Inverse Optimization

    Pouria Fatemi +3

  35. math.OC 2026-05-09 reviewed
    Local LMO matches PGD rates without bounded sets or curvature

    Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle

    Peter Richt\'arik +2

  36. stat.ML 2026-05-09 reviewed
    Two encoder blocks suffice for optimal Transformer approximation

    Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity

    Zhongjie Shi +1

  37. cs.MS 2026-05-09 reviewed
    GPU solver speeds up entropic optimal transport calculations

    cuRegOT: A GPU-Accelerated Solver for Entropic-Regularized Optimal Transport

    Yixuan Qiu

  38. stat.ML 2026-05-09 reviewed
    Canonical diffusion isolates mode barriers from samples and scores

    Measuring and Decomposing Mode Separation via the Canonical Diffusion

    Shaul Tolkovsky +2

  39. cs.CV 2026-05-09 reviewed
    Spectral analysis tracks shape and color defects in unregistered 4D point clouds

    Simultaneous Monitoring of Shape and Surface Color via 4D Point Clouds: A Registration-free Approach

    Mariafrancesca Patalano +2

  40. math.ST 2026-05-09 reviewed
    Estimators achieve minimax optimal rates for unbalanced transport-growth pairs

    Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport

    Donlapark Ponnoprat +2

  41. stat.ML 2026-05-09 reviewed
    Core-halo split removes bias in decentralized fixed-point solving

    Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems

    Haixiang +6

  42. math.ST 2026-05-09 reviewed
    Bayesian PINNs contract to PDE solutions at near-minimax rates

    Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs

    Yuxuan Zhao +1

  43. stat.ML 2026-05-08 reviewed
    Normalizing flows sharpen conformal prediction regions in multiple dimensions

    CONTRA: Conformal Prediction Region via Normalizing Flow Transformation

    Zhenhan Fang +2

  44. stat.ML 2026-05-08 reviewed
    Multi-component ICA splits into decoupled and competition phases

    Learnability and Competition in High-Dimensional Multi-Component ICA

    Eser Ilke Genc +2

  45. cs.LG 2026-05-08 reviewed
    WLM learns second-order population dynamics from snapshots

    A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots

    Vincent Guan +2

  46. cs.LG 2026-05-08 reviewed
    Learns second-order population mechanics from snapshots

    A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots

    Vincent Guan +2

  47. cs.LG 2026-05-08 reviewed
    WLM learns second-order population dynamics from snapshots

    A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots

    Vincent Guan +2

  48. stat.ML 2026-05-08 reviewed
    Sliced inner-product GW distance aligns high-dim data scalably

    Sliced Inner Product Gromov-Wasserstein Distances

    Xiaoyun Gong +2

  49. stat.ML 2026-05-08 reviewed
    Sinkhorn divergence tests full distributional treatment effects

    Sinkhorn Treatment Effects: A Causal Optimal Transport Measure

    Medha Agarwal +1

  50. cs.LG 2026-05-08 reviewed
    Sinks equal hard attention switches at lower cost than diagonals

    Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention

    Peter S\'uken\'ik +3