No article text was recorded for this version.
non-smooth loss landscapes
Version 1 of 140 papers53 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On the Generalization Properties of Adversarial Training
- Blog: Finding Actual Descent Directions for Adversarial Training
- Blog: Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
- Blog: On the Algorithmic Stability of Adversarial Training
- Blog: $H$-Consistency Guarantees for Regression
- Blog: Relationship Between Nonsmoothness in Adversarial Training, Constraints of Attacks, and Flatness in the Input Space
- Blog: Uniformly Stable Algorithms for Adversarial Training and Beyond
- Blog: Adversarial Robust Generalization of Graph Neural Networks
- Blog: Understanding and correcting pathologies in the training of learned optimizers
- Blog: LoRAM: Low-Rank Adaptation of Large Language Models on Manifold
- Blog: GradAuto: Energy-Oriented Attack on Dynamic Neural Networks
- Blog: Adversarial robustness in discontinuous spaces via alternating sampling & descent
- Blog: Random Sharpness-Aware Minimization
- Blog: Adversarially Robust Learning via Entropic Regularization
- Blog: Proximal Splitting Adversarial Attack for Semantic Segmentation
- Blog: Generative Adversarial Equilibrium Solvers
- Blog: Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies (Extended Abstract)
- Blog: Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations
- Blog: Rethinking ResNets: improved stacking strategies with high-order schemes for image classification
- Blog: Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks
- Blog: An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networks
- Blog: LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate
- Blog: Easing non-convex optimization with neural networks
- Blog: How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?
- Blog: Theoretical Limits of Pipeline Parallel Optimization and Application to Distributed Deep Learning
- Blog: Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing
- Blog: Normalization Matters in Zero-Shot Learning
- Blog: Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
- Blog: Automatically Learning Compact Quality-aware Surrogates for Optimization Problems
- Blog: Enhancing Mixup-based Semi-Supervised Learning with Explicit Lipschitz Regularization
- Blog: Stability Analysis and Generalization Bounds of Adversarial Training
- Blog: Differentiable Particle Filtering via Entropy-Regularized Optimal Transport
- Blog: Exploiting the Local Parabolic Landscapes of Adversarial Losses to Accelerate Black-Box Adversarial Attack
- Blog: Optimal Rates in Continual Linear Regression via Increasing Regularization
- Blog: Efficient Sensitivity Analysis for Parametric Robust Markov Chains
- Blog: Generalization Bounds for Adversarial Metric Learning
- Blog: DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization
- Blog: Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy
- Blog: Generalized Strategic Classification and the Case of Aligned Incentives
- Blog: What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_non_smooth_loss_landscapes_532807cb,
title = {non-smooth loss landscapes},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-smooth-loss-landscapes/rdr_532807cb15b54a4fb919d9c82b67a2a7},
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_non_smooth_loss_landscapes_532807cb_v1,
title = {non-smooth loss landscapes},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-smooth-loss-landscapes/rdr_532807cb15b54a4fb919d9c82b67a2a7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}