No article text was recorded for this version.
loss landscape curvature sensitivity
Version 1 of 110 papers18 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Differentially Private Empirical Risk Minimization under the Fairness Lens
- Blog: Pre-training Differentially Private Models with Limited Public Data
- Blog: Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
- Blog: Make Landscape Flatter in Differentially Private Federated Learning
- Blog: Differentially Private Sharpness-Aware Training
- Blog: Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
- Blog: DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
- Blog: Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms
- Blog: In-Distribution Public Data Synthesis With Diffusion Models for Differentially Private Image Classification
- Blog: Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models
History & citation
Current · Permanent link
- This direction split from Navigating Flat Landscapes for Differentially Private Deep Learning (80% overlap)
- This direction split from The Privacy-Utility Trade-off in Differentially Private Learning (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_loss_landscape_curvature_sensitivity_f433c194,
title = {loss landscape curvature sensitivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-curvature-sensitivity/rdr_f433c194bf854afa8f839fe576ebc9df},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_loss_landscape_curvature_sensitivity_f433c194_v1,
title = {loss landscape curvature sensitivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-curvature-sensitivity/rdr_f433c194bf854afa8f839fe576ebc9df/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}