pith. sign in

archive

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

2684 papers in stat.ML · page 6

  1. stat.ML 2026-05-14 reviewed
    Product kernels recover saturation and multiple descent in high-dim KRR

    Large Dimensional Kernel Ridge Regression: Extending to Product Kernels

    Yang Zhou +3

  2. stat.ML 2026-05-14 reviewed
    Eigenvector alignment in kernels drives generalization in regression

    On Kernel Eigen-alignments of KRR: Reconstruction and Generalization

    Yang Liu +3

  3. cs.LG 2026-05-14 reviewed
    Correlated models miscalibrate under Brier aggregation

    When Individually Calibrated Models Become Collectively Miscalibrated

    Zhaohui Wang

  4. cs.LG 2026-05-14 reviewed
    NN radii converge almost surely under polynomial mixing

    Nearest-Neighbor Radii under Dependent Sampling

    Yuanyuan Gao +2

  5. cs.LG 2026-05-14 reviewed
    LLM priors guide source selection in cold-start adaptation

    Language-Induced Priors for Domain Adaptation

    Qiyuan Chen +2

  6. cs.LG 2026-05-14 reviewed
    Mixed gradients keep RL unbiased in hybrid discrete-continuous spaces

    Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients

    Matias Alvo +2

  7. cs.LG 2026-05-14 reviewed
    Target penalty induces bounded weights even with disjoint supports

    TILT: Target-induced loss tilting under covariate shift

    Kakei Yamamoto +1

  8. stat.ML 2026-05-14 reviewed
    Moment matching lets diffusion sampling skip neural training

    Training-Free Generative Sampling via Moment-Matched Score Smoothing

    Zhenyu Yao +1

  9. stat.ML 2026-05-14 reviewed
    Pooled conformal calibration forces coverage or size distortion

    On the Burden of Achieving Fairness in Conformal Prediction

    Ziang Gao +5

  10. stat.ML 2026-05-14 reviewed
    Conformal prediction fairness forces a coverage-size trade-off

    On the Burden of Achieving Fairness in Conformal Prediction

    Ziang Gao +5

  11. cs.LG 2026-05-13 reviewed
    MSSP restores learning-rate transfer in scaled Mixture-of-Experts

    How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization

    Leena Chennuru Vankadara +4

  12. cs.LG 2026-05-13 reviewed
    Score matching yields polynomial sample bounds for polynomial families

    Finite Sample Bounds for Learning with Score Matching

    Devin Smedira +4

  13. stat.ML 2026-05-13 reviewed
    Mean shift particles approximate integrals from unnormalized densities

    To discretize continually: Mean shift interacting particle systems for Bayesian inference

    Ayoub Belhadji +2

  14. stat.ML 2026-05-13 reviewed
    Conformal method bounds confident errors in CoT reasoning

    Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning

    Yu Gu +3

  15. cond-mat.dis-nn 2026-05-13 reviewed
    Ising networks store continuous signals near 0.5 capacity

    Finite-size scaling of hetero-associative retrieval in continuous-signal-driven Ising spin systems

    Andrea Ladiana

  16. cs.LG 2026-05-13 reviewed
    TabPFN-3 tops tabular benchmarks in a single forward pass

    TabPFN-3: Technical Report

    L\'eo Grinsztajn +40

  17. quant-ph 2026-05-13 reviewed
    Classical algorithm samples neural lottery tickets in poly(D) time

    Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm

    Natsuto Isogai +3

  18. stat.ML 2026-05-13 reviewed
    Valiant learnability equals poly-size query compression

    What is Learnable in Valiant's Theory of the Learnable?

    Steve Hanneke +3

  19. cs.LG 2026-05-13 reviewed
    Hybrid VAE isolates scanner effects in brain connectomes

    Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling

    Gaurav Rudravaram +19

  20. cs.LG 2026-05-13 reviewed
    Entropic RL policy identification matches lower bound

    Tight Sample Complexity Bounds for Entropic Best Policy Identification

    Amer Essakine +1

  21. cs.LG 2026-05-13 reviewed
    Reasoning models sample tree languages exactly with log n memory

    A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning

    Jason Gaitonde +4

  22. cs.LG 2026-05-13 reviewed
    Marginal bridges cut denoising error in flow language models

    Sampling from Flow Language Models via Marginal-Conditioned Bridges

    Iskander Azangulov +1

  23. stat.ML 2026-05-13 reviewed
    Package turns anomaly scores into calibrated p-values

    Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with 'nonconform'

    Oliver Hennh\"ofer +2

  24. cs.LG 2026-05-13 reviewed
    Single-loop actor-critic hits Õ(ε^{-2}) sample rate

    Achieving $\epsilon^{-2}$ Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions

    Ishaq Hamza +1

  25. cs.LG 2026-05-13 reviewed
    Deep learning reduces to layerwise low-degree spectral filtering

    Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning

    Yatin Dandi +4

  26. stat.ML 2026-05-13 reviewed
    Two auxiliary environments identify any nonlinear causal graph

    Causal Learning with the Invariance Principle

    Francesco Montagna +1

  27. stat.ML 2026-05-13 reviewed
    Adaptive internal preprocessing beats external searches on 42 of 57 NIRS datasets

    Reframing preprocessing selection as model-internal calibration in near-infrared spectroscopy: A large-scale benchmark of operator-adaptive PLS and Ridge models

    Gregory Beurier +4

  28. stat.ML 2026-05-13 reviewed
    NIR calibration absorbs preprocessing into the model

    Reframing preprocessing selection as model-internal calibration in near-infrared spectroscopy: A large-scale benchmark of operator-adaptive PLS and Ridge models

    Gregory Beurier +4

  29. stat.ML 2026-05-13 reviewed
    Reused diffusion latents incur error from subspace misalignment

    On the Limits of Latent Reuse in Diffusion Models

    Yifeng Yu +1

  30. cs.LG 2026-05-13 reviewed
    Rescaled stepsizes remove bias in async SGD

    Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity

    Ammar Mahran +2

  31. cs.LG 2026-05-13 reviewed
    Trajectory augmentation enables offline RL from limited suboptimal data

    Trajectory-Level Data Augmentation for Offline Reinforcement Learning

    Tobias Schm\"ahling +2

  32. cs.LG 2026-05-13 reviewed
    Flow matching conditioning is kernel smoothing

    Support-Conditioned Flow Matching Is Kernel Smoothing

    Daniel Matsui Smola

    2 Piths
  33. stat.ML 2026-05-13 reviewed
    Perturbation cuts online FDR regret from linear to sqrt(T)

    A Regret Perspective on Online Multiple Testing

    Qingyang Hao +3

  34. cs.LG 2026-05-13 reviewed
  35. stat.ML 2026-05-13 reviewed
    Learned continuous perturbations boost LLM extrapolation to new domains

    Learning Perturbations to Extrapolate Your LLM

    Zetai Cen +5

  36. stat.ML 2026-05-13 reviewed
    Activation split removes dequant bottleneck in LLM inference

    Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference

    Lingchao Zheng +7

  37. cs.LG 2026-05-13 reviewed
    High-rank PINNs generalize despite differential operators

    Unified generalization analysis for physics informed neural networks

    Yuka Hashimoto +1

  38. stat.ML 2026-05-13 reviewed
    Change-point sample needs depend on both jumps and positions

    The Sample Complexity of Multiple Change Point Identification under Bandit Feedback

    Maximilian Graf +1

  39. stat.ML 2026-05-13 reviewed
    One template inequality unifies data-dependent generalization bounds

    A Survey on Data-Dependent Worst-Case Generalization Bounds

    Hubert Leroux +2

  40. stat.ML 2026-05-13 reviewed
    Entropy rises with missing context in LLMs

    LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information

    Stef van Buuren

  41. stat.ML 2026-05-13 reviewed
    The paper proposes a likelihood-free Bayesian filtering method using coupling-informed…

    Coupling-Informed Transport Maps for Bayesian Filtering in Nonlinear Dynamical Systems

    Dengfei Zeng +3

  42. stat.ML 2026-05-13 reviewed
    Kernels on parameters deliver bounds for nonlinear BO models

    Kernel-based guarantees for nonlinear parametric models in Bayesian optimization

    Rafael Oliveira

  43. stat.ML 2026-05-13 reviewed
    GP construction keeps mean identical across repetitions with smooth variation

    Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process

    Elias Reich +2

  44. stat.ML 2026-05-13 reviewed
    Hallucination limits in AI imaging fixed by forward model alone

    On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods

    David Iagaru +3

  45. stat.ML 2026-05-13 reviewed
    Neural nets learn time series clusters from simulations

    Amortized Neural Clustering of Time Series based on Statistical Features

    \'Angel L\'opez-Oriona +1

  46. stat.ML 2026-05-13 reviewed
    Wavelet DPPs deliver better minibatch variance reduction

    State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives

    Hoang-Son Tran +3

  47. stat.ML 2026-05-13 reviewed
    Covariance estimate lifts few-step diffusion sampling

    Covariance-aware sampling for Diffusion Models

    Andrea Schioppa +1

  48. stat.ML 2026-05-13 reviewed
    Pre-trained net selects kernels for high-dim density estimates

    Adaptive Kernel Density Estimation with Pre-training

    Ruitong Zhang +1

  49. stat.ML 2026-05-13 reviewed
    Adaptive sampling fixes bias in fast FP8 RL rollouts

    AIS: Adaptive Importance Sampling for Quantized RL

    Jiajun Zhou +4

  50. stat.ML 2026-05-13 reviewed
    Coreset surrogate equals Wasserstein gap in flow matching

    Coreset-Induced Conditional Velocity Flow Matching

    Xiao Wang +2