pith. sign in

archive

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

2684 papers in stat.ML · page 1

  1. stat.ML 2026-05-22 reviewed
    SHK flow perturbations give dimension-free DP bounds

    On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy

    Aratrika Mustafi +1

  2. cs.LG 2026-05-22 reviewed
    Damped looping of transformer blocks lifts accuracy on frozen models

    Training-Free Looped Transformers

    Lizhang Chen +4

  3. stat.ML 2026-05-22 reviewed
    Muon dynamics dissipate Hamiltonian energy monotonically

    Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer

    Aratrika Mustafi +2

  4. cs.LG 2026-05-22 reviewed
    The paper derives entrywise error bounds for spectral ranking in the Bradley-Terry-Luce…

    Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries

    Dongmin Lee +2

  5. cs.LG 2026-05-22 reviewed
    Derivative bound yields linear sampling for regularized classification

    Optimal Dimension-Free Sampling for Regularized Classification

    Meysam Alishahi +3

  6. stat.ML 2026-05-22 reviewed
    Preference feedback yields sublinear regret in kernel MDPs

    Learning Kernel-Based MDPs from Episodic Preferential Feedback

    Nikola Pavlovic +2

  7. stat.ML 2026-05-22 reviewed
    Dirichlet model inside MC Dropout improves uncertainty calibration

    Dirichlet-Based Monte Carlo Dropout for Uncertainty Estimation in Neural Networks

    Rouaa Hoblos (FEMTO-ST) +3

  8. stat.ML 2026-05-22 reviewed
    Sparse activations split scaling laws into two exponents

    Asymmetric Scaling Laws from Sparse Features

    John Sous +1

  9. stat.ML 2026-05-22 reviewed
    Joint noise and DAG estimation handles varying variances

    Concomitant DAG Learning: On the Roles of Noise Adaptivity, Sparsity, and Non-negativity

    Gonzalo Mateos +3

  10. cs.LG 2026-05-22 reviewed
    Adaptive allocation matches oracle rate for multi-judge LLM scoring

    Instance-Optimal Estimation with Multiple LLM Judges on a Budget

    Junghyun Lee +4

  11. cs.CL 2026-05-22 reviewed
    Next-token prediction works only if text prefixes suffice for latent context

    When Is Next-Token Prediction Useful? Marginalization, Ergodicity, Mixture Identifiability, Local Sufficiency, RAG, Tools, and Programming

    Francesco Corielli

  12. stat.ML 2026-05-22 reviewed
    Joint training avoids error inheritance from weak privileged data

    Coupled Training with Privileged Information and Unlabeled Data

    Jiahao Shi +2

  13. cs.LG 2026-05-22 reviewed
    Symmetric noise lifts AlpacaEval scores from 65% to 69% in fine-tuning

    Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning

    Abhay Yadav

  14. cs.LG 2026-05-22 reviewed
    Limit space makes any-size input models universal

    Any-Dimensional Invariant Universality

    Shengtai Yao +2

  15. eess.SY 2026-05-22 reviewed
    Lifted operators turn hybrid models into convex kernel mixtures

    Convex Hybrid Modeling: An Operator-Based Approach

    Wentao Tang

  16. stat.ML 2026-05-22 reviewed
    Gradient descent recovers true similarity metric from triplets

    Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models

    Conlan Olson +3

  17. cs.LG 2026-05-22 reviewed
    Gen-ROTDA adapts bike-sharing demand models across years by anchoring on few target labels

    Robust OT-Guided Generative Residual Domain Adaptation for Bike-Sharing Demand Prediction under Temporal Domain Shift

    Yiming Ma

  18. stat.ML 2026-05-21 reviewed
    LLM Sparsity Prior lets spike-and-slab models ignore bad LLM weights

    LLM Sparsity Prior for Robust Feature Selection

    Caleb Skinner +2

  19. math.NA 2026-05-21 reviewed
    Mass-orthogonality penalty yields consistent mode shapes from sparse data

    Mode-Shape Expansion Using Physics-Constrained Gaussian Process Regression

    Farid Ghahari

  20. stat.ML 2026-05-21 reviewed
    KAN estimator converges independent of covariate dimension

    KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis

    Stelios Boulitsakis Logothetis +2

  21. cs.LG 2026-05-21 reviewed
    One config matches tuned AdamW across 1-8x horizons on LLMs

    Anytime Training with Schedule-Free Spectral Optimization

    Anuj Apte +4

  22. cs.CL 2026-05-21 reviewed
    Hawkes process lifts late alignment in news text simulations

    HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation

    Zewei Deng +2

  23. q-bio.QM 2026-05-21 reviewed
    Bayesian models match frequentist SHD classification with better uncertainty

    Uncertainty-aware classification and triage of structural heart disease using electrocardiography and echocardiography metrics

    Mitchel J. Colebank

  24. stat.ML 2026-05-21 reviewed
    Diffusion denoising score matching keeps bounds stable as modes separate

    Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation

    Benedikt L\"utke Schwienhorst +2

  25. cs.LG 2026-05-21 reviewed
    Entropy regularization needs non-degenerate information forces to work

    Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning

    Kim Phuc Tran

  26. cs.LG 2026-05-21 reviewed
  27. stat.ML 2026-05-21 reviewed
    Kernel density gradients yield conservative drifting at rate N^{-1/(d+4)}

    Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models

    Krishnakumar Balasubramanian

  28. cs.LG 2026-05-21 reviewed
    Diffusion model generates continuous survival times from censored data

    SDPM: Survival Diffusion Probabilistic Model for Continuous-Time Survival Analysis

    Stanislav R. Kirpichenko +2

  29. cs.LG 2026-05-21 reviewed
    Leave-one-out predictor fixes uniform diffusion mismatch

    Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

    Samson Gourevitch +6

  30. cs.LG 2026-05-21 reviewed
    Plug-in losses approximate EDL objectives with decaying error

    Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier

    Berk Hayta +3

  31. cs.LG 2026-05-21 reviewed
    Proxy method sets new accuracy standard for Shapley interactions

    Proxy-Based Approximation of Shapley and Banzhaf Interactions

    Santo M. A. R. Thies +5

  32. cs.LG 2026-05-21 reviewed
    ProxySHAP lowers error in Shapley interaction estimates

    Proxy-Based Approximation of Shapley and Banzhaf Interactions

    Santo M. A. R. Thies +5

  33. cs.LG 2026-05-21 reviewed
    Multi-task operator learning matches single-task rates

    Multiple Neural Operators Achieve Near-Optimal Rates for Multi-Task Learning

    Adrien Weihs +1

  34. cs.CL 2026-05-21 reviewed
    Hyperfitting expands final LLM layer to promote rare tokens

    Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion

    Meimingwei Li +3

  35. stat.ML 2026-05-21 reviewed
    Martingale kernel tests replace permutations with normal quantiles

    A Martingale Kernel Independence Test

    Felix Laumann +2

  36. cs.LG 2026-05-21 reviewed
    Value functions create straight paths for generative transport

    Generative Modeling by Value-Driven Transport

    Pablo Moreno-Mu\~noz +2

  37. stat.ML 2026-05-21 reviewed
    Algorithms achieve optimal bidding rates despite feedback shilling

    Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions

    Luigi Foscari +2

  38. cs.NE 2026-05-21 reviewed
    Description length post-selection lifts GP regression accuracy

    Guiding Multi-Objective Genetic Programming with Description Length Improves Symbolic Regression Solutions

    Gabriel Kronberger +4

  39. cs.LG 2026-05-21 reviewed
    Selective neuron fusion trades ensemble accuracy for lower cost

    Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation

    Fabian Morelli +1

  40. stat.ML 2026-05-21 reviewed
    Regular graphs make ASE and LSE subspaces identical

    The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers

    Minh Triet Pham +1

  41. cs.LG 2026-05-21 reviewed
    GPU batches cut optimal sparse GLM search time by 10-100 times

    From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs

    Jiachang Liu +1

  42. stat.ML 2026-05-21 reviewed
    Betting wealth bound yields empirical Bernstein LIL

    From Betting to Empirical Bernstein LIL

    Francesco Orabona

  43. cs.LG 2026-05-21 reviewed
    Physics-informed model recovers aerodynamic loads from noisy bridge data

    Aerodynamic force reconstruction using physics-informed Gaussian processes

    Gledson Rodrigo Tondo +2

  44. stat.ML 2026-05-21 reviewed
    Finite networks track mean-field limit uniformly in time

    Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks

    Margalit Glasgow +1

  45. math.ST 2026-05-21 reviewed
    Optimal mean estimators must have sensitivity Omega(eta + sqrt(eta d/n))

    Robust Statistical Estimators with Bounded Empirical Sensitivity

    Valentio Iverson +3

  46. stat.ME 2026-05-21 reviewed
    Equal-variance structural VARs identified only up to orthogonal transforms and scale

    Causal Discovery in Structural VAR Models Under Equal Noise Variance

    SeyedSina Seyedi HasanAbadi +3

  47. cs.LG 2026-05-20 reviewed
    Symbolic search recovers exact discrete distribution formulas

    Symbolic Density Estimation for Discrete Distributions

    Ziwen Liu +1

  48. stat.CO 2026-05-20 reviewed
    Truncation makes neural likelihood work for long state sequences

    Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models

    Kostas Tsampourakis +1

  49. cs.LG 2026-05-20 reviewed
    KL divergence to GPs splits into three costs for neural processes

    Three Costs of Amortizing Gaussian Process Inference with Neural Processes

    Robin Young

  50. stat.ME 2026-05-20 reviewed
    Estimator gives valid vaccine effectiveness from TND data with gaps

    Targeted maximum likelihood estimation of vaccine effectiveness and immune correlates in test-negative design studies with missing data

    Leah I. B. Andrews +2