pith. sign in

archive

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

2684 papers in stat.ML · page 10

  1. cs.CL 2026-05-08 reviewed
    Semantic sampling yields unbiased calibration metric for open QA

    A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering

    Zhanliang Wang +5

  2. stat.ML 2026-05-08 reviewed
    AM-PPI narrows CIs 10-40% by routing cases to right predictor

    Active Multiple-Prediction-Powered Inference

    Nicholas Brawand +6

  3. cs.LG 2026-05-08 reviewed
    Queryable LoRA routes shared low-rank atoms by network state

    Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms

    Omatharv Bharat Vaidya +3

  4. math.ST 2026-05-08 reviewed
    Log d time recovers latent Hawkes networks

    On Observation Time for Recovering Latent Hawkes Networks

    Jonas Linkerh\"agner +4

  5. cs.LG 2026-05-08 reviewed
    Deep Sets require embedding dimension linear in set size for universality

    Embedding Dimension Lower Bounds for Universality of Deep Sets and Janossy Pooling

    Ali Syed +2

  6. cs.LG 2026-05-08 reviewed
    Newton method converges exponentially for infinite-width neural nets

    Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit

    Konstantin Riedl +2

  7. cs.LG 2026-05-08 reviewed
    Newton method reaches zero loss exponentially fast in wide neural nets

    Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit

    Konstantin Riedl +2

  8. stat.ML 2026-05-08 reviewed
    Bounded Gaussian surface area allows non-negative L1 approximations

    A Note on Non-Negative $L_1$-Approximating Polynomials

    Jane H. Lee +2

  9. stat.ME 2026-05-08 reviewed
  10. astro-ph.SR 2026-05-08 reviewed
    Deep learning infers red-giant seismic parameters from short TESS data

    Inferring Asteroseismic Parameters from Short Observations Using Deep Learning: Application to TESS and K2 Red Giants

    Nipun Ghanghas +4

  11. stat.ML 2026-05-08 reviewed
    Test pinpoints locations where treatments alter outcome distributions

    Semiparametric Efficient Test for Interpretable Distributional Treatment Effects

    Houssam Zenati +1

  12. cs.LG 2026-05-08 reviewed
    This paper proposes shifting LLM judges from full substitutes to auxiliary tools in a…

    Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need?

    Jane Paik Kim

  13. math.OC 2026-05-08 reviewed
    Penalty methods reach ε-KKT points for bilevel minimax problems in Õ(ε^{-4}) steps

    Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems

    Yiyang Shen +3

  14. cs.LG 2026-05-08 reviewed
    Encoder trained on pairs scales inference to sets of thousands

    It Just Takes Two: Scaling Amortized Inference to Large Sets

    Antoine Wehenkel +3

  15. stat.ML 2026-05-08 reviewed
    Bayes predictives make confidence sequences asymptotically log-optimal

    Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means

    Valentin Kilian +2

  16. stat.ML 2026-05-08 reviewed
    Bayes-assisted sequences match oracle efficiency for bounded means

    Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means

    Valentin Kilian +2

  17. stat.ML 2026-05-08 reviewed
    Single gradient flow solves inverse problems at low cost

    Consistency Regularised Gradient Flows for Inverse Problems

    Alessio Spagnoletti +3

  18. stat.ML 2026-05-08 reviewed
    Target correction equates online kernel regression to offline

    Characterizing and Correcting Effective Target Shift in Online Learning

    Ziyan Li +1

  19. cs.LG 2026-05-08 reviewed
    Chance-level black-box classification decays exponentially with more queries

    Black-box model classification under the discriminative factorization

    Hayden Helm +2

  20. cond-mat.dis-nn 2026-05-08 reviewed
    MuP keeps spectral outliers width-independent in deep linear nets

    Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer

    Clarissa Lauditi +2

  21. cond-mat.dis-nn 2026-05-08 reviewed
    Outlier modes in deep network spectra grow consistently across widths

    Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer

    Clarissa Lauditi +2

  22. cs.LG 2026-05-08 reviewed
    Attention beats Fourier for PDEs on irregular shapes

    When Attention Beats Fourier: Multi-Scale Transformers for PDE Solving on Irregular Domains

    Brandon Yee +3

  23. stat.ML 2026-05-08 reviewed
    EM convergence governed by missing-information operator

    Expectation-Maximization as a Spectrally Governed Relaxation Flow

    Qiao Wang

  24. cs.LG 2026-05-08 reviewed
    POETS performs KL-regularized Thompson sampling via LLM policy ensembles

    POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles

    Nicolas Menet +2

  25. stat.ML 2026-05-08 reviewed
    Flow matching on raw counts beats baselines with fewer parameters

    Flow Matching for Count Data

    Ganchao Wei +1

  26. stat.ML 2026-05-08 reviewed
    Learned topology maximizes Fisher information in lensing maps

    TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information

    Matteo Biagetti +5

  27. stat.ML 2026-05-08 reviewed
    Counterfactuals generated as deconfounding flows from observations

    Debiased Counterfactual Generation via Flow Matching from Observations

    Hugh Dance +3

  28. stat.ML 2026-05-08 reviewed
    Prefix consistency weights CoT votes to match accuracy at 4.6x fewer tokens

    Reliable Chain-of-Thought via Prefix Consistency

    Naoto Iwase +3

  29. math.ST 2026-05-08 reviewed
    FHDMs match minimax rates for spherical data

    Statistical Convergence of Spherical First Hitting Diffusion Models

    Simon Bienewald +1

  30. stat.ML 2026-05-08 reviewed
    New bound makes contrastive learning scale with class count

    A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning

    Nong Minh Hieu +1

  31. stat.ML 2026-05-08 reviewed
    Contrastive learning bounds scale only with number of classes

    A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning

    Nong Minh Hieu +1

  32. cs.LG 2026-05-08 reviewed
    Energy minimization yields weight-tied layers matching Transformer baselines

    Revisiting Transformer Layer Parameterization Through Causal Energy Minimization

    Jin Xu +4

  33. cs.AI 2026-05-08 reviewed
    Bayesian optimization discovers tasks with only log regret overhead

    Open-Ended Task Discovery via Bayesian Optimization

    Masaki Adachi +2

  34. cs.LG 2026-05-08 reviewed
  35. cs.LG 2026-05-08 reviewed
    Masked-position latent prediction beats MLM on protein tasks

    ProteinJEPA: Latent prediction complements protein language models

    Dan Ofer +2

  36. stat.ME 2026-05-08 reviewed
  37. stat.ML 2026-05-08 reviewed
    Trained Transformers admit spectrum-adaptive generalization bounds

    Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers

    Mana Sakai +1

  38. eess.SP 2026-05-08 reviewed
    Energy subtraction on paired elements recovers signed OTA aggregates

    Resource-Element Energy Difference for Noncoherent Over-the-Air Federated Learning

    Hao Chen +1

  39. eess.SP 2026-05-08 reviewed
    Energy difference on two resources replaces CSI for wireless federated learning

    Resource-Element Energy Difference for Noncoherent Over-the-Air Federated Learning

    Hao Chen +1

  40. cs.LG 2026-05-08 reviewed
    Calibrated noise on single samples yields unbiased private gradients

    Modulated learning for private and distributed regression with just a single sample per client device

    Praneeth Vepakomma +3

  41. cs.LG 2026-05-08 reviewed
    Bernstein bonus improves kernel RL regret bound

    Improved Model-based Reinforcement Learning with Smooth Kernels

    Kun Long +2

  42. cs.LG 2026-05-08 reviewed
    New algorithm matches lower bounds on cost in reward-constrained bandits

    Cost-Ordered Feasibility for Multi-Armed Bandits with Cost Subsidy

    Ishank Juneja +2

  43. cs.LG 2026-05-08 reviewed
    Token overlaps perturb template rules but graph geometry can preserve margins

    When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification

    Wenjie Guan +1

  44. stat.ML 2026-05-08 reviewed
    Learned rule extends finite cluster trees to arbitrary depth

    Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples

    Yicen Li +4

  45. cs.LG 2026-05-08 reviewed
    Bandit policy logs regret on upper-quantile targets

    Conformal-Style Quantile Analyses for Stochastic Bandits

    Chengyu Du +1

  46. cs.IT 2026-05-08 reviewed
    MLE attains sub-Gaussian tails and entropic normality

    Sub-Gaussian Concentration and Entropic Normality of the Maximum Likelihood Estimator

    Leighton P. Barnes +1

  47. cs.LG 2026-05-08 reviewed
    Poisson-Moreau drift yields near-optimal almost sure rates for Markovian SA

    Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift

    Xinyu Liu +2

  48. cs.MA 2026-05-08 reviewed
    Diffusion policies fix exploration limits in multi-agent RL

    Decentralized Diffusion Policy Learning for Enhanced Exploration in Cooperative Multi-agent Reinforcement Learning

    Yuyang Zhang +2

  49. stat.ML 2026-05-08 reviewed
    Averaging trajectory errors calibrates conformal sets for diffusion models

    TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models

    Zhenhan Fang +2

  50. stat.ML 2026-05-08 reviewed
    Fixed neural networks with definable layers have finite PAC sample complexity

    Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity

    Anastasis Kratsios +4