pith. sign in

archive

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

2684 papers in stat.ML · page 8

  1. math.AT 2026-05-11 reviewed
    Stable barcodes track how dependency clusters evolve in dynamic Bayesian networks

    A Stable Distance Persistence Homology for Dynamic Bayesian Network Clustering

    Will Bales +1

  2. stat.ML 2026-05-11 reviewed
    Thompson sampling learns unknown networks while optimizing treatments

    Adaptive Policy Learning Under Unknown Network Interference

    Aidan Gleich +2

  3. cs.LG 2026-05-11 reviewed
    Random spectra match Muon on GPT-2 training

    Muon is Not That Special: Random or Inverted Spectra Work Just as Well

    Zakhar Shumaylov +8

  4. stat.ML 2026-05-11 reviewed
    Kernel makes rotated 3D anisotropy explicit in Gaussian processes

    Interpretable Machine Learning for Spatial Science: A Lie-Algebraic Kernel for Rotationally Anisotropic Gaussian Processes

    Kane Warrior +1

  5. cs.CV 2026-05-11 reviewed
    CutMix training induces local attention in early ViT layers

    Inducing Spatial Locality in Vision Transformers through the Training Protocol

    Eduardo Santiago Toledo +1

  6. stat.ME 2026-05-11 reviewed
    Predictive resampling yields exact Bayesian posteriors

    Variational predictive resampling

    Laura Battaglia +4

  7. stat.ME 2026-05-11 reviewed
    VPR with mean-field predictives matches exact posteriors

    Variational predictive resampling

    Laura Battaglia +4

  8. cs.IT 2026-05-11 reviewed
    Synthesize likelihoods to meet accuracy bounds with minimal prior deviation

    Sensor Design for Accuracy-Bounded Estimation via Maximum-Entropy Likelihood Synthesis

    Raktim Bhattacharya

  9. cs.LG 2026-05-11 reviewed
    Neural tilting of Lévy measures enables jump-preserving SDE inference

    Variational Inference for L\'evy Process-Driven SDEs via Neural Tilting

    Yaman Kindap +4

  10. cs.LG 2026-05-11 reviewed
    k-step policy gradients escape myopic traps in restricted MDPs

    Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy Gradients

    Alex DeWeese +1

  11. stat.ML 2026-05-11 reviewed
    Transformer states converge uniformly to ODEs at rate O(1/L + 1/(L^{1/3} sqrt(H)))

    Uniform Scaling Limits in AdamW-Trained Transformers

    William Gibson +1

  12. cs.AI 2026-05-11 reviewed
    Reasoning helps LLM judges only on hard tasks

    Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge

    Wenbo Zhang +3

  13. stat.ML 2026-05-11 reviewed
    Linear networks store facts up to p log p = d²/2

    Factual recall in linear associative memories: sharp asymptotics and mechanistic insights

    Alessio Giorlandino +2

  14. math.ST 2026-05-11 reviewed
    Finite VC dimension enables finite-sample tests for distribution trade-offs

    When Are Trade-Off Functions Testable from Finite Samples?

    Kaining Shi +2

  15. cs.LG 2026-05-11 reviewed
    Tail extrapolation approximates best-of-N gradients from m much smaller than N

    What should post-training optimize? A test-time scaling law perspective

    Muheng Li +2

  16. stat.ML 2026-05-11 reviewed
    LASSO matches homogeneous threshold for mixed-quality sparse data

    Price of Quality: Sufficient Conditions for Sparse Recovery using Mixed-Quality Data

    Youssef Chaabouni +1

  17. cs.LG 2026-05-11 reviewed
    Natural policy gradient equals smoothed policy iteration

    Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework

    Phalguni Nanda +1

  18. cs.CL 2026-05-11 reviewed
    LLM personas match human survey distributions on stable questions

    When Can Digital Personas Reliably Approximate Human Survey Findings?

    Mumin Jia +3

  19. cs.LG 2026-05-11 reviewed
    Divide-and-conquer causal discovery extends to latent variables

    A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables

    Zheng Li +5

  20. stat.ML 2026-05-11 reviewed
    Amortized networks speed up causal sensitivity bounds by orders of magnitude

    Amortizing Causal Sensitivity Analysis via Prior Data-Fitted Networks

    Emil Javurek +4

  21. stat.ML 2026-05-11 reviewed
    Bayesian linear solvers are special cases of affine PIMs

    Affine Tracing: A New Paradigm for Probabilistic Linear Solvers

    Disha Hegde +2

  22. cs.CV 2026-05-11 reviewed
    Confidence weights fuse modalities for long-tailed recognition

    Simultaneous Long-tailed Recognition and Multi-modal Fusion for Highly Imbalanced Multi-modal Data

    Heegeon Yoon +1

  23. math.OC 2026-05-11 reviewed
    Bound certifies any learned controller for unknown linear systems

    A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems

    Yujia Luo +3

  24. math.OC 2026-05-11 reviewed
    PAC-Bayes bound guarantees controller performance on unknown systems

    A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems

    Yujia Luo +3

  25. cs.LG 2026-05-11 reviewed
    Semi-simulated tests pick different winners than real data for treatment effects

    Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation

    George Panagopoulos

  26. stat.ME 2026-05-11 reviewed
    Covariate-dependent level links low-fidelity quantiles to high-fidelity ones

    Multi-Fidelity Quantile Regression

    Yixiang Liu +1

  27. stat.ML 2026-05-11 reviewed
    Sharp jumps in feature overlap set optimal neural scaling laws

    Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks

    Minh-Toan Nguyen +1

  28. stat.ML 2026-05-11 reviewed
    Mass lift certifies regret in guided diffusion optimization

    Regret Analysis of Guided Diffusion for Black-Box Optimization over Structured Inputs

    Masaki Adachi +3

  29. stat.ML 2026-05-11 reviewed
    Low-fidelity data yields kernels for high-fidelity PDE solving

    Multifidelity Gaussian process regression for solving nonlinear partial differential equations

    Fatima-Zahrae El-Boukkouri +2

  30. stat.ML 2026-05-11 reviewed
    Unified taxonomy clarifies ML uncertainty for physics

    Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation

    Manuel Hau{\ss}mann +2

  31. stat.ML 2026-05-11 reviewed
    Expert losses cut MoE training time for time series

    Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration

    Btissame El Mahtout +1

  32. stat.ML 2026-05-11 reviewed
    Test error in augmented random features depends only on data and augmentation moments

    Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation

    Lucas Morisset +2

  33. cs.LG 2026-05-11 reviewed
    Anchored TS safely reduces regret using shifted offline data

    Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift

    Bochao Li +3

  34. cs.LG 2026-05-11 reviewed
    Median anchoring cuts regret in online bandits with shifted offline data

    Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift

    Bochao Li +3

  35. stat.ML 2026-05-11 reviewed
    Neural feature maps scale exact GP inference

    Scalable Gaussian process inference via neural feature maps

    Anthony Stephenson

  36. cs.CV 2026-05-11 reviewed
    Focal sets plus fuzzy logic tame uncertainty in hierarchical image labels

    A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classification

    Ezel Kilicdere +2

  37. cs.LG 2026-05-11 reviewed
    Deeper Picard iterations cut truncation error without unbounded estimation error

    Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs

    Koichi Taniguchi +1

  38. math.ST 2026-05-11 reviewed
    GAN method estimates full causal distributions with minimax optimality

    Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality

    Shu Tamano +1

  39. cs.LG 2026-05-11 reviewed
    Scaling rules transfer hyperparameters from small to large DenseAMs

    Hyperparameter Transfer for Dense Associative Memories

    Roi Holtzman +2

  40. stat.ML 2026-05-11 reviewed
    Cyclic LiNG models coarsen to identifiable low-dimensional DAGs

    Coarsening Linear Non-Gaussian Causal Models with Cycles

    Francisco Madaleno +2

  41. stat.ML 2026-05-11 reviewed
    Subsampled CLT turns PFN predictions into valid Thompson samples

    PFN-TS: Thompson Sampling for Contextual Bandits via Prior-Data Fitted Networks

    Yan Shuo Tan +5

  42. cs.LG 2026-05-11 reviewed
    Kaplan-Meier estimators give unbiased ARL and ADD for finite sequences

    Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis

    Taiki Miyagawa +1

  43. cs.LG 2026-05-11 reviewed
    Generative models show an innovation window before memorizing data

    The two clocks and the innovation window: When and how generative models learn rules

    Binxu Wang +2

  44. stat.ML 2026-05-11 reviewed
    Wasserstein projection gives optimal private sampling

    Differentially Private Sampling from Distributions via Wasserstein Projection

    Shokichi Takakura +2

  45. stat.ML 2026-05-11 reviewed
    Federated LLMs keep explicit consistency and coverage under bandwidth budgets

    Federated Language Models Under Bandwidth Budgets: Distillation Rates and Conformal Coverage

    Prasanjit Dubey +1

  46. cs.LG 2026-05-11 reviewed
    Order-gap measure gives stopping rule for adaptive learning

    Consolidation-Expansion Operator Mechanics:A Unified Framework for Adaptive Learning

    Debashis Guha

  47. cs.LG 2026-05-11 reviewed
    Order-gap tracks distance to settled state in learning systems

    Consolidation-Expansion Operator Mechanics:A Unified Framework for Adaptive Learning

    Debashis Guha

  48. stat.ML 2026-05-11 reviewed
    Multicalibration corrected without clean labels using contamination matrices

    Unified Approach for Weakly Supervised Multicalibration

    Futoshi Futami +1

  49. stat.ML 2026-05-11 reviewed
    Rectified AI laws cut bias in Bayesian priors from limited data

    Supercharging Bayesian Inference with Reliable AI-Informed Priors

    Jongwoo Choi +1

  50. cs.LG 2026-05-10 reviewed
    Kernel regression error bounds cover non-Gaussian noise

    On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise

    Johannes Teutsch +4