AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Tractable Sharpness-Aware Learning of Probabilistic Circuits

Hrithik Suresh, Sahil Sidheekh, Vishnu Shreeram M P, Sriraam Natarajan, Narayanan Chatapuram Krishnan

AAAI 2026 · Optimization › Implicit bias and generalization · approach: Stability-based generalization analysis · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Hessian-trace regularizer (gradient-based)Einsum Network · Synthetic manifolds, 1% datatest NLL reduction (%): 49.53 mean reduction; 65.71 DoF; 89.24 sharpnessImproved
add Hessian-trace regularizer (gradient-based)Einsum Network · Synthetic manifolds, 100% datatest NLL reduction (%): 5.05 mean reduction; 0.49 DoF; 35.25 sharpnessImproved
add Hessian-trace regularizer (gradient-based)Einsum Network · Synthetic manifolds, twisted_eight 100% datatest NLL reduction (%): -1.22Hurt
add Hessian-trace regularized EMPyJuice HCLT · Binary density, 1% datatest NLL reduction (%): 7.12 mean; 8.81 DoF; 23.04 sharpnessImproved
add Hessian-trace regularized EMPyJuice HCLT · Binary density, 5% datatest NLL reduction (%): 2.19 mean; 5.79 DoF; 15.32 sharpnessImproved
add Hessian-trace regularized EMPyJuice HCLT · Binary density, 50% datatest NLL reduction (%): -0.48 NLL; 0.21 DoF; 5.55 sharpnessHurt
add Hessian-trace regularized EMPyJuice HCLT · Binary density, 100% datatest NLL reduction (%): -0.31 NLL; 0.06 DoF; 4.04 sharpnessHurt
add Hessian-trace regularized EMPyJuice HCLT · Binary density, dna 1% datatest NLL reduction (%): 29.45Improved
increase regularization strength mu beyond 0.1 (ablation)PyJuice HCLT · DNA 5% splitvalidation NLL: small mu in (0, 0.1] captures most gains; larger mu marginal gains at cost of slight underfittingMixed
use sum-squared-gradient trace instead of autograd Hessian traceEinsum Network · 2D spiral, network depth scalingcomputation time: autograd runtime exponential blow up vs linear scaling for SSGImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy