pith. sign in

archive

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

2684 papers in stat.ML · page 4

  1. stat.ML 2026-05-18 reviewed
    Riesz basis yields closed-form ANOVA for dependent inputs

    Generalized Functional ANOVA in Closed-Form: A Unified View of Additive Explanations

    Baptiste Ferrere +3

  2. math.NA 2026-05-18 reviewed
    Volterra signature computed in quadratic or better time

    Computational aspects of the Volterra Signature

    Paul P. Hager +3

  3. stat.ML 2026-05-18 reviewed
    Quantile error in heavy-tailed projections splits into three parts

    On Stability and Decomposition of Sample Quantiles under Heavy-Tailed Distributions

    Choudur Lakshminarayan

  4. stat.ML 2026-05-18 reviewed
    Heavy-tailed quantiles split into direction shift

    On Stability and Decomposition of Sample Quantiles under Heavy-Tailed Distributions

    Choudur Lakshminarayan

  5. stat.ML 2026-05-18 reviewed
    Generalized posteriors fix overconfidence in misspecified network models

    Bayesian Latent Space Models for Graphs Are Misspecified: Toward Robust Inference via Generalized Posteriors

    Aldric Labarthe (CB +1

  6. cs.CV 2026-05-18 reviewed
    RAE v2 reaches SOTA gFID 1.06 in 80 epochs on ImageNet

    Improved Baselines with Representation Autoencoders

    Jaskirat Singh +5

  7. math.OC 2026-05-18 reviewed
    Attention learns PCA eigenvectors from Gaussian data

    Attention-based PCA

    Rodrigo Maulen-Soto (LPSM +2

  8. stat.ML 2026-05-18 reviewed
    Dictionary of spectral operators approximates dynamical systems manifold

    Geometric Dictionary Learning of Dynamical Systems with Optimal Transport

    Thibaut Germain +4

  9. stat.ML 2026-05-18 reviewed
    Learned noising speeds discrete diffusion sampling

    Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster

    Grigory Bartosh +3

  10. stat.ML 2026-05-18 reviewed
    Ridge regularization distorts feature-learning networks at vanishing strength

    Canonical Regularisation of Wide Feature-Learning Neural Networks

    George Whittle +4

    4 Piths
  11. cs.LG 2026-05-18 reviewed
    Ringmaster LMO recovers optimal async time complexity for LMO

    Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method

    Abdurakhmon Sadiev +3

    1 Piths
  12. math.OC 2026-05-18 reviewed
    Symmetry-respecting updates beat AdamW in LLM pretraining

    Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers

    Tim Tsz-Kit Lau +1

  13. stat.ML 2026-05-18 reviewed
    DDPMs reach optimal Wasserstein bounds in any dimension

    Wasserstein bounds for denoising diffusion probabilistic models via the F\"ollmer process

    Yuta Koike

  14. cs.DS 2026-05-18 reviewed
  15. stat.ML 2026-05-18 reviewed
    Föllmer process sets DDPM sampler parameters naturally

    A note on connections between the F\"ollmer process and the denoising diffusion probabilistic model

    Yuta Koike

  16. cs.LG 2026-05-18 reviewed
    Frequency extraction recovers hidden generalization at 80% noise

    Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise

    Linyu Liu +1

  17. stat.ML 2026-05-18 reviewed
    Neural nets learn densities from empirical characteristic functions

    A data-driven Fourier-mixture neural-network method for density estimation

    Duy-Minh Dang +1

  18. cs.LG 2026-05-18 reviewed
    Deep ensembles with recalibrated Gaussian negative log-likelihood loss deliver stronger…

    Uncertainty Reliability Under Domain Shift: An Investigation for Data-Driven Blood Pressure Estimation in Photoplethysmography

    Mohammad Moulaeifard +3

  19. cs.LG 2026-05-18 reviewed
    Cost-sensitive regression scales decision-focused learning

    Scalable Decision-Focused Learning through Cost-Sensitive Regression

    Noah Schutte +4

  20. math.OC 2026-05-18 reviewed
    Newton method on Wasserstein space escapes saddles to global minima

    From Saddle Points Toward Global Minima: A Newton-Type Method on Wasserstein Space

    Razvan-Andrei Lascu +1

  21. cs.LG 2026-05-18 reviewed
    Mirrored unlearning boosts data attribution in diffusion models

    Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

    Joan Serr\`a +4

  22. stat.ME 2026-05-18 reviewed
    C-SymmPI achieves near-conditional coverage for symmetric structured data

    Conditional Predictive Inference for General Structured Data with Group Symmetries

    Yichen Shen +1

  23. stat.ML 2026-05-18 reviewed
    Girsanov weights enable unbiased resampling for diffusion models

    Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures

    Chenyang Wang +4

  24. cs.LG 2026-05-18 reviewed
    f-divergence drifts share a universal velocity form

    A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows

    Chenguang Wang +1

  25. math.ST 2026-05-18 reviewed
    s-step self-distillation optimizes shrinkage for s-spike covariances

    Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models

    Radu Lecoiu +2

  26. stat.ML 2026-05-18 reviewed
    Two GD steps yield floor(α2/(0.5-α1)) learned directions

    Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent

    Behrad Moniri +1

  27. stat.ML 2026-05-18 reviewed
    Two GD steps produce multiple outliers in linear-width weights

    Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent

    Behrad Moniri +1

  28. stat.ME 2026-05-18 reviewed
    Test compares two categorical Gini correlations for predictor importance

    Comparing Two Categorical Gini Correlations with Applications to Classification Problems

    Sameera Hewage +1

  29. cs.LG 2026-05-18 reviewed
    New measure exactly bounds full swap regret and tests from small samples

    Testable and Actionable Calibration for Full Swap Regret

    Konstantina Bairaktari +3

  30. stat.ML 2026-05-18 reviewed
    Statistical analysis designs better quantizers for deep nets

    StatQAT: Statistical Quantizer Optimization for Deep Networks

    Mehmet Aktukmak +2

  31. stat.ML 2026-05-18 reviewed
    Large gradient step yields target-spiked features and adaptive kernel

    How does feature learning reshape the function space?

    Jo\~ao Lobo +3

  32. stat.ML 2026-05-18 reviewed
    Online method gives coverage bounds for panel data forecasts

    Online Conformal Prediction for Non-Exchangeable Panel Data

    Daohong Tu +1

  33. stat.ML 2026-05-17 reviewed
    Averaged Q-learning iterates converge to Gaussian at n^{-1/4} rate

    On Gaussian approximation for entropy-regularized Q-learning with function approximation

    Artemy Rubtsov +4

  34. math.OC 2026-05-17 reviewed
    Gradient flow reaches global minima for infinite-depth transformers

    Training Infinitely Deep and Wide Transformers

    Rapha\"el Barboni +3

    4 Piths
  35. stat.ME 2026-05-17 reviewed
    Kernel optimization controls FDR across structured hypotheses

    Controlling False Discovery in Arbitrarily Structured Hypothesis Spaces via Reproducing Kernels

    Binyamin Perets +1

  36. physics.data-an 2026-05-17 reviewed
    Physical properties guide Bayesian selection of spectral peaks

    Integrating Bayesian Spectral Deconvolution and Expert Scientific Reasoning for Robust Peak Estimation

    Hayato Okubo +7

  37. cs.LG 2026-05-17 reviewed
    Bregman framework gives U-calibration for Tsallis losses

    Calibeating for general proper losses: A Bregman divergence approach

    Maximilian Fichtl +2

  38. cs.LG 2026-05-17 reviewed
    Regret-optimal algorithms for position-aware MNL bandits

    Learning in Position-Aware Multinomial Logit Bandits: From Multiplicative to General Position Effects

    Xi Chen +3

  39. cs.LG 2026-05-17 reviewed
    Adjoint equations remove S-dependence from discrete diffusion convergence

    Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space

    Kelvin Kan +5

  40. stat.ML 2026-05-16 reviewed
    Noisy matrix completion cuts samples to side info dimension

    Sample-efficient inductive matrix completion with noise and inexact side-information

    Yuepeng Yang +1

  41. cs.LG 2026-05-16 reviewed
    Nonlinear heads escape collapse by generating negative curvature

    The Geometry of Projection Heads: Conditioning, Invariance, and Collapse

    Faris Chaudhry

  42. math.OC 2026-05-16 reviewed
    SGD on diagonal linear networks converges exponentially to zero risk

    High-dimensional Limit of SGD for Diagonal Linear Networks

    Bego\~na Garc\'ia Malaxechebarr\'ia +3

  43. stat.ME 2026-05-16 reviewed
    Spectral sparsification keeps MTP2 graphs accurate while making them sparse

    Learning Gaussian Graphical Models under Total Positivity via Spectral Graph Sparsification

    Ignacio Echave-Sustaeta Rodr\'iguez +2

  44. stat.ML 2026-05-16 reviewed
    Multi-task estimator achieves optimal rates with weaker assumptions

    Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety

    Seok-Jin Kim

  45. cs.LG 2026-05-16 reviewed
    Fairness layer guarantees output parity in neural networks

    Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning

    David Troxell +2

  46. stat.ML 2026-05-16 reviewed
    New network learns SPDE solutions and their uncertainty from noisy data

    Diffusion-Based Stochastic Operator Networks for Uncertainty Quantification in Stochastic Partial Differential Equations

    Phuoc-Toan Huynh +2

  47. stat.ML 2026-05-16 reviewed
    Anchored transport forecasts next distributions from causal context

    CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series

    Jiecheng Lu +3

  48. stat.ML 2026-05-16 reviewed
    SGD needs over N^3 log^2 N steps for phase-only classification

    A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights

    Fabiola Ricci +2

  49. stat.ML 2026-05-16 reviewed
    Intensity model generates hypergraphs with fidelity and novelty

    HYVINT: Intensity-Driven Hypergraph Generation with Variational Representations

    Xinyi Hong +2

  50. stat.ML 2026-05-16 reviewed
    Stable-blanket predictors match or beat causal parents after interventions

    Prediction-Intervention Games and Invariant Sets

    Linus K\"uhne +2