No article text was recorded for this version.
loss landscape curvature analysis
Version 2 of 2292 papers353 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
- Blog: The asymptotic spectrum of the Hessian of DNN throughout training
- Blog: Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks
- Blog: Rényi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization
- Blog: Implicit Jacobian regularization weighted with impurity of probability output
- Blog: On the Power-Law Spectrum in Deep Learning: A Bridge to Protein Science
- Blog: SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing
- Blog: A Universal Class of Sharpness-Aware Minimization Algorithms
- Blog: Feature-Robustness, Flatness and Generalization Error for Deep Neural Networks
- Blog: Generalization in fully-connected neural networks for time series forecasting
- Blog: SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing
- Blog: Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
- Blog: Information-Theoretic Perspectives on Optimizers
- Blog: Local Geometry of Nonconvex Spike Deconvolution From Low-Pass Measurements
- Blog: Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
- Blog: A Reparameterization-Invariant Flatness Measure for Deep Neural Networks
- Blog: HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
- Blog: Mixability is Bayes Risk Curvature Relative to Log Loss
- Blog: Rényi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization
- Blog: Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
- Blog: Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
- Blog: Assessing Local Generalization Capability in Deep Models
- Blog: Flatness Guided Test-Time Adaptation for Vision-Language Models
- Blog: Detecting underdetermination in parameterized quantum circuits
- Blog: LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection
- Blog: Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training
- Blog: Optimizing Variational Representations of Divergences and Accelerating Their Statistical Estimation
- Blog: Generalization Measures for Zero-Shot Cross-Lingual Transfer
- Blog: Understanding and Robustifying Differentiable Architecture Search
- Blog: Super Consistency of Neural Network Landscapes and Learning Rate Transfer
- Blog: Stochastic Gradient Descent with Noise of Machine Learning Type Part II: Continuous Time Analysis
- Blog: Symmetry Breaking in Symmetric Tensor Decomposition
- Blog: Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
- Blog: Accelerating Neural Network Training Along Sharp and Flat Directions
- Blog: Loss Landscape Analysis for Reliable Quantized ML Models for Scientific Sensing
- Blog: CR-SAM: Curvature Regularized Sharpness-Aware Minimization
- Blog: Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks
- Blog: Sharpness-Aware Training for Free
- Blog: Gradient Norm Regularizer Seeks Flat Minima and Improves Generalization
- Blog: Generalization in fully-connected neural networks for time series forecasting
- Blog: Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
- Blog: Hessian-based toolbox for reliable and interpretable machine learning in physics
- Blog: Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
- Blog: LensLLM: Unveiling Fine-Tuning Dynamics for LLM Selection
- Blog: Hessian Eigenspectra of More Realistic Nonlinear Models
- Blog: Data-induced multiscale losses and efficient multirate gradient descent schemes
- Blog: The instabilities of large learning rate training: a loss landscape view
- Blog: PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
- Blog: On the interplay between noise and curvature and its effect on optimization and generalization
- Blog: Model Selection and Stability in k-means Clustering
- Blog: Generalisation under gradient descent via deterministic PAC-Bayes
- Blog: Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
- Blog: Flat minima generalize for low-rank matrix recovery
- Blog: Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
- Blog: On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
- Blog: Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
- Blog: A Closer Look at Smoothness in Domain Adversarial Training
- Blog: Singularity of the Hessian in Deep Learning
- Blog: Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
- Blog: The Loss Landscape of Deep Linear Neural Networks: a Second-order Analysis
Showing 60 of 292 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_loss_landscape_curvature_analysis_f2ce67f0,
title = {loss landscape curvature analysis},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-curvature-analysis/rdr_f2ce67f0aeed44f2866b0b9d54abb879},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_loss_landscape_curvature_analysis_f2ce67f0_v2,
title = {loss landscape curvature analysis},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-curvature-analysis/rdr_f2ce67f0aeed44f2866b0b9d54abb879/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}