Text to Figure文生图poster

Leverage SHAP: Shapley Values via Leverage Sampling

A conference poster presenting Leverage SHAP, a method for estimating Shapley values using leverage score sampling. It covers theoretical guarantees, least squares formulation, and experimental comparisons against Kernel SHAP on various datasets.

论文上下文

Paper title: Provably Accurate Shapley Value Estimation via Leverage Score Sampling Abstract: A conference poster presenting Leverage SHAP, a method for estimating Shapley values using leverage score sampling. It covers theoretical guarantees, least squares formulation, and experimental comparisons against Kernel SHAP on various datasets. Paper body (method & results): <!DOCTYPE html> <html lang="en"> <head> <meta content="text/html; charset=utf-8" http-equiv="content-type"/> <title>Provably Accurate Shapley Value Estimation via Leverage Score Sampling</title>  <meta content="width=device-width, initial-scale=1, shrink-to-fit=no" name="viewport"/> <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/ar5iv.0.7.9.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/ar5iv-fonts.0.7.9.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/latexml_styles.css" rel="stylesheet" type="text/css"/> <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script> <script src="https://cdnjs.cloudflare.com/ajax/libs/html2canvas/1.3.3/html2canvas.min.js"></script> <script src="/static/browse/0.3.4/js/addons_new.js"></script> <script src="/static/browse/0.3.4/js/feedbackOverlay.js"></script> <base href="/html/2410.01917v1/"/></head> <body> <nav class="ltx_page_navbar"> <nav class="ltx_TOC"> <ol class="ltx_toclist"> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S1" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">1 </span>Introduction</span></a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S1.SS1" title="In 1 Introduction ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">1.1 </span>Efficient Shapley Value Computation</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S1.SS2" title="In 1 Introduction ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">1.2 </span>Our Contributions</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"> <a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S1.SS3" title="In 1 Introduction ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">1.3 </span>Related Work</span></a> <ol class="ltx_toclist ltx_toclist_subsection"> <li class="ltx_tocentry ltx_tocentry_paragraph"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S1.SS3.SSS0.Px1" title="In 1.3 Related Work ‣ 1 Introduction ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title">Shapley Values Estimation.</span></a></li> <li class="ltx_tocentry ltx_tocentry_paragraph"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S1.SS3.SSS0.Px2" title="In 1.3 Related Work ‣ 1 Introduction ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title">Leverage Scores.</span></a></li> </ol> </li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S2" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">2 </span>Background and Notation</span></a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_paragraph"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S2.SS0.SSS0.Px1" title="In 2 Background and Notation ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title">Notation.</span></a></li> <li class="ltx_tocentry ltx_tocentry_paragraph"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S2.SS0.SSS0.Px2" title="In 2 Background and Notation ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title">Preliminaries.</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S3" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3 </span>Leverage SHAP</span></a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S3.SS1" title="In 3 Leverage SHAP ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.1 </span>Analytical Form of Leverage Scores</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S3.SS2" title="In 3 Leverage SHAP ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.2 </span>Our Algorithm</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S4" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4 </span>Theoretical Guarantees</span></a></li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S5" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">5 </span>Experiments</span></a></li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S6" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6 </span>Conclusion</span></a></li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#S7" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">7 </span>Acknowledgements</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#A1" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">A </span>Proof of Approximation Guarantee</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#A2" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">B </span>Proof of Approximation Corollary</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#A3" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">C </span>Additional Experiments: Performance by <math alttext="\gamma" class="ltx_Math" display="inline"><semantics><mi>γ</mi><annotation-xml encoding="MathML-Content"><ci>𝛾</ci></annotation-xml><annotation encoding="application/x-tex">\gamma</annotation><annotation encoding="application/x-llamapun">italic_γ</annotation></semantics></math></span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#A4" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">D </span>Additional Experiments: <math alttext="\ell_{2}" class="ltx_Math" display="inline"><semantics><msub><mi mathvariant="normal">ℓ</mi><mn>2</mn></msub><annotation-xml encoding="MathML-Content"><apply><csymbol cd="ambiguous">subscript</csymbol><ci>ℓ</ci><cn type="integer">2</cn></apply></annotation-xml><annotation encoding="application/x-tex">\ell_{2}</annotation><annotation encoding="application/x-llamapun">roman_ℓ start_POSTSUBSCRIPT 2 end_POSTSUBSCRIPT</annotation></semantics></math>-norm error with Ablation</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#A5" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">E </span>Additional Experiments: Linear Objective Error with Ablation</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#A6" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">F </span>Equivalence</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#A7" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">G </span>Sampling Without Replacement</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"> <a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#A8" title="In Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">H </span>Constrained Regression</span></a> <ol class="ltx_toclist ltx_toclist_appendix"> <li class="ltx_tocentry ltx_tocentry_paragraph"><a class="ltx_ref" href="https://arxiv.org/html/2410.01917v1#A8.SS0.SSS0.Px1" title="In Appendix H Constrained Regression ‣ Provably Accurate Shapley Value Estimation via Leverage Score Sampling"><span class="ltx_text ltx_ref_title">Traditional Solution Used in Kernel SHAP</span></a></li> </ol> </li> </ol></nav> </nav> <div class="ltx_page_main"> <div class="ltx_page_content"> <article class="ltx_document ltx_authors_1line"> <h1 class="ltx_title ltx_title_document">Provably Accurate Shapley Value Estimation via Leverage Score Sampling</h1> <div class="ltx_authors"> <span class="ltx_creator ltx_role_author"> <span class="ltx_personname">Christopher Musco & R. Teal Witter <br class="ltx_break"/>New York University <br class="ltx_break"/><span class="ltx_text ltx_font_typewriter" id="id4.1.id1">{cmusco,rtealwitter}@nyu.edu</span> <br class="ltx_break"/> </span></span> </div> <div class="ltx_abstract"> <h6 class="ltx_title ltx_title_abstract">Abstract</h6> <p class="ltx_p" id="id3.3">Originally introduce

完整 Prompt

Above I've shared:
(1) the full paper text,
(2) all paper figures labeled by figure number,
(3) the caption for the central poster figure I'm building.

TASK: This is a CONFERENCE POSTER. **NOT** an academic-paper figure.
Style requirements:

  - Multi-section layout with a clear poster structure: large title banner
    at the top with the paper title + author/affiliation strip, then 3-6
    distinct content panels arranged in columns or a grid.
  - Large legible fonts (text must be readable at 2 m viewing distance) —
    headings ≥ 60 pt visual size in the final image.
  - Use colour blocks / panel backgrounds to delineate sections (this is
    what makes it a poster, not a single-figure diagram).
  - Aspect ratio: portrait or landscape rectangle, NOT square.

If your output looks like a standard academic-paper figure (single panel,
no title banner, dense small text, no colour blocks), you've failed the
task. Render the COMPLETE poster, not just the central figure.

Just give me the final poster image.

立即试用此 Prompt

在生成器中自动预填此 prompt。

试用此 Prompt

Leverage SHAP: Shapley Values via Leverage Sampling

论文上下文

完整 Prompt

立即试用此 Prompt

相关 Prompt

PINN Framework Pipeline for Microscopy Data

DP-FTRL Privacy Amplification Analysis — Conference Poster

NC-TTT: Noise-Contrastive Test-Time Training Poster