pith. sign in

archive

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

2684 papers in stat.ML · page 12

  1. cs.LG 2026-05-07 reviewed
    Low precision triggers slingshot loss spikes via feature inflation

    Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes

    Liu Hanqing +3

  2. stat.ML 2026-05-07 reviewed
    Kernel embeddings define Gaussian mixtures for Hilbert space data

    Gaussian mixture models in Hilbert spaces via kernel methods

    Daniel L\'opez-Montero +2

  3. stat.ML 2026-05-07 reviewed
    TabCF turns tabular models into fast control function estimators

    TabCF: Distributional Control Function Estimation with Tabular Foundation Models

    Geping Chen +4

  4. stat.ML 2026-05-07 reviewed
    Repeated splits fix winner's curse in LLM adaptive benchmarks

    Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking

    Yang Xu +5

  5. cs.LG 2026-05-07 reviewed
    This paper proves that for many kernels

    Sharper Guarantees for Misspecified Kernelized Bandit Optimization

    Davide Maran +1

  6. stat.ML 2026-05-07 reviewed
    Derivatives define causal fairness for continuous attributes

    Tuning Derivatives for Causal Fairness in Machine Learning

    Filip Edstr\"om +3

  7. stat.ML 2026-05-07 reviewed
    CITE certifies target answers as LLM response modes with anytime-valid guarantees

    CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency

    Hirofumi Ota +4

  8. stat.ME 2026-05-07 reviewed
    Kernel copula embeddings detect causal dependence shifts

    Detecting Changes in Causal Dependence with Kernels and Copulas

    Shakeel Gavioli-Akilagun +2

  9. stat.ML 2026-05-07 reviewed
    Ratio-based losses track relative errors via y over f(x)

    Ratio-based Loss Functions

    Lena Helgerth +1

  10. math.ST 2026-05-07 reviewed
    Kernel gradient flows match minimax uniform rates

    Optimal Confidence Band for Kernel Gradient Flow Estimator

    Yuqian Cheng +2

  11. stat.ML 2026-05-07 reviewed
    Transformers execute RL policy updates from context alone

    Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement

    Haodong Liang +1

  12. stat.ML 2026-05-07 reviewed
    Fourier features scale nonlinear causal discovery to mixed data

    Fourier Feature Methods for Nonlinear Causal Discovery: FFML Scoring, TRFF Scoring, and FFCI Testing in Mixed Data

    Joseph D. Ramsey

  13. stat.ML 2026-05-07 reviewed
    Fourier features scale GP scoring and CI tests for nonlinear causal discovery

    Fourier Feature Methods for Nonlinear Causal Discovery: FFML Scoring, TRFF Scoring, and FFCI Testing in Mixed Data

    Joseph D. Ramsey

  14. math.NA 2026-05-07 reviewed
    Convex hulls give O(d/N) error for positive kernel quadrature

    Convex-Geometric Error Bounds for Positive-Weight Kernel Quadrature

    Satoshi Hayakawa

  15. cs.LG 2026-05-07 reviewed
    KAN spline removal degrades time-series forecasts

    Temporal Functional Circuits: From Spline Plots to Faithful Explanations in KAN Forecasting

    Naveen Mysore

  16. stat.ML 2026-05-07 reviewed
    Early spectra forecast token efficiency in LLM training

    Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization

    Andy Zeyi Liu +2

  17. stat.ML 2026-05-07 reviewed
    vMF spherical flows generate categorical data from posterior alone

    Spherical Flows for Sampling Categorical Data

    Jannis Chemseddine +2

  18. stat.ML 2026-05-07 reviewed
    Spherical vMF flow reduces categorical sampling to scalar ODE

    Spherical Flows for Sampling Categorical Data

    Jannis Chemseddine +2

  19. cs.LG 2026-05-07 reviewed
    Residual from spectral analysis flags grokking transitions early

    Distributional Spectral Diagnostics for Localizing Grokking Transitions

    Ziyue Wang +2

  20. cs.LG 2026-05-07 reviewed
    This paper develops a new algorithm for setting prices dynamically when customer demand…

    Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand

    Jianyu Xu +1

  21. stat.ML 2026-05-07 reviewed
    Neural score from backward PDE defines posterior SDE for sparse smoothing

    Variational Smoothing and Inference for SDEs from Sparse Data with Dynamic Neural Flows

    Yu Wang +1

  22. stat.ML 2026-05-07 reviewed
    Pretrained transformer solves PU classification in one forward pass

    In-Context Positive-Unlabeled Learning

    Siyan Liu +4

  23. stat.ML 2026-05-07 reviewed
    Relaxed Cholesky method scales causal discovery to 10k variables

    Relaxed Sparsest-Permutation Formulation for Causal Discovery at Scale

    Sunmin Oh +2

  24. stat.ML 2026-05-06 reviewed
    Symmetry-aware nets learn non-stationary GP kernels scalably

    Permutation-preserving Functions and Neural Vecchia Covariance Kernels

    Jian Cao +2

  25. cs.LG 2026-05-06 reviewed
    Diffusion priors sharpen rain maps from microwave links

    Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors

    Badr Moufad +6

  26. cs.LG 2026-05-06 reviewed
    Pathwise gradients optimize non-myopic feature acquisition

    Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients

    Linus Aronsson +1

  27. cs.LG 2026-05-06 reviewed
    Linear attribution methods share one canonical form

    GRALIS: A Unified Canonical Framework for Linear Attribution Methods via Riesz Representation

    Raimondo Fanale

  28. cs.LG 2026-05-06 reviewed
    Linear attribution methods share one canonical form

    GRALIS: A Unified Canonical Framework for Linear Attribution Methods via Riesz Representation

    Raimondo Fanale

  29. stat.ML 2026-05-06 reviewed
    Benign regularizer exposes hidden local convexity in nonconvex matrix estimation

    Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation

    Chengyu Cui +1

  30. stat.ML 2026-05-06 reviewed
    Gradient matching recovers hidden penalties in neural net training

    Estimating Implicit Regularization in Deep Learning

    Joseph H. Rudoler +3

  31. math.ST 2026-05-06 reviewed
    Direct estimator gives finite-sample bounds for Schr odinger bridge drifts

    Direct Estimation of Schr\"odinger Bridge Time-Series Drifts: Finite-Sample, Asymptotic, and Adaptive Guarantees

    Othmane Mazhar +1

  32. cs.LG 2026-05-06 reviewed
    Adaptive elastic nets fix feature starvation in sparse autoencoders

    Feature Starvation as Geometric Instability in Sparse Autoencoders

    Faris Chaudhry +2

  33. stat.ML 2026-05-06 reviewed
    Linear memory reaches n capacity with listwise but only n/log n with top-1

    Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval

    Nicholas Barnfield +4

  34. cs.LG 2026-05-06 reviewed
    Cumulant approximations estimate wide MLP outputs with fewer FLOPs

    Estimating the expected output of wide random MLPs more efficiently than sampling

    Wilson Wu +5

  35. cs.LG 2026-05-06 reviewed
    Wide random MLPs yield expected outputs without sampling

    Estimating the expected output of wide random MLPs more efficiently than sampling

    Wilson Wu +5

  36. cs.LG 2026-05-06 reviewed
    Drifting models match Wasserstein flow fixed points on KL

    On the Wasserstein Gradient Flow Interpretation of Drifting Models

    Arthur Gretton +5

  37. cs.LG 2026-05-06 reviewed
    GMD targets fixed points of Wasserstein gradient flows

    On the Wasserstein Gradient Flow Interpretation of Drifting Models

    Arthur Gretton +5

  38. cs.LG 2026-05-06 reviewed
    Distributional regret bounds unify bandits and episodic RL

    Unified Framework of Distributional Regret in Multi-Armed Bandits and Reinforcement Learning

    Harin Lee +1

  39. cs.GR 2026-05-06 reviewed
    Bayesian view selection cuts scans needed for task-specific 3D models

    A Bayesian Approach for Task-Specific Next-Best-View Selection with Uncertain Geometry

    Jingsen Zhu +2

  40. stat.ML 2026-05-06 reviewed
    Decomposing coefficients by graph nodes yields stable doubly sparse regression

    Proximal Projection for Doubly Sparse Regularized Models

    Jia Wei He +2

  41. math.ST 2026-05-06 reviewed
    High-dimensional statistics connects to optimization and random matrices

    High-Dimensional Statistics: Reflections on Progress and Open Problems

    Arian Maleki +11

  42. stat.ML 2026-05-06 reviewed
    Diffusion on incidence matrices generates better hypergraphs

    Hypergraph Generation via Structured Stochastic Diffusion

    Christopher Nemeth

  43. stat.ML 2026-05-06 reviewed
    MDL method finds spatial regions and their time series drivers

    Scalable inference of spatial regions and temporal signatures from time series

    Jiayu Weng +1

  44. cs.LG 2026-05-06 reviewed
    Adaptivity advantages shift under ReLU realizability

    Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning

    Anastasis Kratsios +2

  45. cs.LG 2026-05-06 reviewed
    Batch normalization refines local affine partitions during training

    Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks

    Xuan Qi +5

  46. cs.LG 2026-05-06 reviewed
    BN recenters hyperplanes to refine local partitions in networks

    Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks

    Xuan Qi +5

  47. stat.ML 2026-05-06 reviewed
    Directional energy in drift subspace bounds frozen predictor risk

    Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift

    Jonathan R. Landers

  48. cs.LG 2026-05-06 reviewed
    Causal GRN methods beat correlations only in clean data

    When Does Gene Regulatory Network Inference Break? A Controlled Diagnostic Study of Causal and Correlational Methods on Single-Cell Data

    Miguel Fernandez-de-Retana +4

  49. cs.LG 2026-05-06 reviewed
    Regime score flips Bayesian optimization winners across budgets

    Regime-Conditioned Evaluation in Multi-Context Bayesian Optimization

    Noel Thomas

  50. cs.LG 2026-05-06 reviewed
    Symmetric attention diagnostics miss flow direction

    Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics

    Dominik Dahlem +2