No article text was recorded for this version.
loss landscape smoothing (loss landscape flattening)
Version 1 of 1149 papers196 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Robustness via Curvature Regularization, and Vice Versa
- Blog: Designing Robust Quantum Neural Networks via Optimized Circuit Metrics
- Blog: Likelihood Landscapes: A Unifying Principle Behind Many Adversarial Defenses
- Blog: Jacobian Adversarially Regularized Networks for Robustness
- Blog: Improving Adversarial Robustness via Attention and Adversarial Logit Pairing
- Blog: Flatness-aware Adversarial Attack
- Blog: Towards Adversarially Robust Dataset Distillation by Curvature Regularization
- Blog: Self-Progressing Robust Training
- Blog: Compositional Curvature Bounds for Deep Neural Networks
- Blog: Learn from the Past: A Proxy based Adversarial Defense Framework to Boost Robustness
- Blog: Noise Augmentation Is All You Need For FGSM Fast Adversarial Training: Catastrophic Overfitting And Robust Overfitting Require Different Augmentation
- Blog: AdvRush: Searching for Adversarially Robust Neural Architectures
- Blog: Towards Adversarially Robust Dataset Distillation by Curvature Regularization
- Blog: Regularizers for Single-step Adversarial Training
- Blog: Regularizer to Mitigate Gradient Masking Effect During Single-Step Adversarial Training
- Blog: Adversarial Defense Via Local Flatness Regularization
- Blog: Flooding-X: Improving BERT's Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning
- Blog: Learning to Generate Noise for Multi-Attack Robustness
- Blog: AdvRush: Searching for Adversarially Robust Neural Architectures
- Blog: Adversarial Robustness through Regularization: A Second-Order Approach
- Blog: Efficient local linearity regularization to overcome catastrophic overfitting
- Blog: Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks
- Blog: Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack
- Blog: Quadratic Upper Bound for Boosting Robustness
- Blog: Compositional Curvature Bounds for Deep Neural Networks
- Blog: Efficient Defenses Against Adversarial Attacks
- Blog: Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
- Blog: Fast Adversarial Training with Noise Augmentation: A Unified Perspective on RandStart and GradAlign
- Blog: Second Order Optimization for Adversarial Robustness and Interpretability
- Blog: Bridging the Performance Gap between FGSM and PGD Adversarial Training
- Blog: Interpolation between Residual and Non-Residual Networks
- Blog: Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks
- Blog: Adversarial Distributional Training for Robust Deep Learning
- Blog: Geometry-Aware Instrumental Variable Regression
- Blog: Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training
- Blog: On the Security Risks of AutoML
- Blog: Improving the Generalization of Adversarial Training with Domain Adaptation
- Blog: Towards Calibrated Losses for Adversarial Robust Reject Option Classification
- Blog: GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
- Blog: Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning
- Blog: Explainable Learning: Implicit Generative Modelling during Training for Adversarial Robustness
- Blog: Robustness via curvature regularization, and vice versa
- Blog: On the uncertainty principle of neural networks
- Blog: AdaGAT: Adaptive Guidance Adversarial Training for the Robustness of Deep Neural Networks
- Blog: A Non-monotonic Smooth Activation Function
- Blog: Adversarial Defense Via Local Flatness Regularization
- Blog: Hessian-Free Second-Order Adversarial Examples for Adversarial Learning
- Blog: Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless lp Norm Solution for Fast Adversarial Training
- Blog: The Dark Side: Security Concerns in Machine Learning for EDA
- Blog: First Line of Defense: A Robust First Layer Mitigates Adversarial Attacks
- Blog: Partially Recentralization Softmax Loss for Vision-Language Models Robustness
- Blog: Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training
- Blog: Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
- Blog: Quadratic Upper Bound for Boosting Robustness
- Blog: Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness
- Blog: Security Consideration For Deep Learning-Based Image Forensics
- Blog: Interpretation of Neural Networks Is Fragile
- Blog: Continuous Time Analysis of Momentum Methods
- Blog: Enhancing Robustness in Incremental Learning with Adversarial Training
- Blog: Analyzing Neural Network Robustness Using Graph Curvature
Showing 60 of 149 papers.
History & citation
Current · Permanent link
- Flattening the Loss Landscape with Curvature Regularization merged into this direction (76% overlap)
- Adversarial Robustness through Loss Landscape Engineering merged into this direction (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_loss_landscape_smoothing_loss_landscape__ab10cb4a,
title = {loss landscape smoothing (loss landscape flattening)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-smoothing-loss-landscape-flattening/rdr_ab10cb4adf7f4706870ed7b494c96102},
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_smoothing_loss_landscape__ab10cb4a_v1,
title = {loss landscape smoothing (loss landscape flattening)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-smoothing-loss-landscape-flattening/rdr_ab10cb4adf7f4706870ed7b494c96102/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}