No article text was recorded for this version.
binary-to-multiclass generalization
Version 2 of 260 papers64 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On Robust Multiclass Learnability
- Blog: On the Role of Randomization in Adversarially Robust Classification
- Blog: The Adversarial Consistency of Surrogate Risks for Binary Classification
- Blog: Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker
- Blog: Calibration and Consistency of Adversarial Surrogate Losses
- Blog: Fast Provably Robust Decision Trees and Boosting
- Blog: Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory
- Blog: Origins of Low-Dimensional Adversarial Perturbations
- Blog: A Maximum K-Min Approach for Classification
- Blog: Learning with Monotone Adversarial Corruptions
- Blog: Adversarial Risk via Optimal Transport and Optimal Couplings
- Blog: Randomization for adversarial robustness: the Good, the Bad and the Ugly
- Blog: Learning with Noisy Labels
- Blog: Adversarial consistency and the uniqueness of the adversarial bayes classifier
- Blog: Efficient Optimization Algorithms for Linear Adversarial Training
- Blog: Certified Adversarial Robustness Under the Bounded Support Set
- Blog: Being Properly Improper
- Blog: Detection of Iterative Adversarial Attacks via Counter Attack
- Blog: Provably robust boosted decision stumps and trees against adversarial attacks
- Blog: Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise
- Blog: Robust Logistic Regression and Classification
- Blog: Binary Classification Under ℓ0 Attacks for General Noise Distribution
- Blog: Diverse Adversaries for Mitigating Bias in Training
- Blog: TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
- Blog: Randomized Smoothing of All Shapes and Sizes
- Blog: On Symmetric Losses for Learning from Corrupted Labels
- Blog: Instance Reweighting Adversarial Training Based on Confused Label
- Blog: A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications
- Blog: Fast Provably Robust Decision Trees and Boosting
- Blog: MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples
- Blog: Weight-covariance alignment for adversarially robust neural networks
- Blog: Boosting in the presence of label noise
- Blog: Adversarial Risk via Optimal Transport and Optimal Couplings
- Blog: Certified Adversarial Robustness Under the Bounded Support Set
- Blog: A PAC-Bayes Analysis of Adversarial Robustness
- Blog: A Stochastic Neural Network for Attack-Agnostic Adversarial Robustness
- Blog: CERT-ED: Certifiably Robust Text Classification for Edit Distance
- Blog: Resilient Linear Classification: An Approach to Deal with Attacks on Training Data
- Blog: Binary Classification Under $\ell_0$ Attacks for General Noise Distribution
- Blog: Certifiably Robust Encoding Schemes
- Blog: On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
- Blog: Analysis of classifiers' robustness to adversarial perturbations
- Blog: Adversarial Surrogate Risk Bounds for Binary Classification
- Blog: Certified Robustness via Locally Biased Randomized Smoothing
- Blog: A PAC-Bayes Analysis of Adversarial Robustness
- Blog: A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs
- Blog: Robustness Guarantees for Adversarially Trained Neural Networks
- Blog: The Benefits of Adversarial Defence in Generalisation
- Blog: Theoretically Principled Trade-off between Robustness and Accuracy
- Blog: The Many Faces of Adversarial Risk
- Blog: Regularized Robustly Reliable Learners and Instance Targeted Attacks
- Blog: Certifiable Out-of-Distribution Generalization
- Blog: Theoretical Analysis of Adversarial Learning: A Minimax Approach
- Blog: Adversarial Surrogate Risk Bounds for Binary Classification
- Blog: Towards Consistency in Adversarial Classification
- Blog: Multi-Task Adversarial Network for Disentangled Feature Learning
- Blog: Efficient Training of Robust Decision Trees Against Adversarial Examples
- Blog: Benign Overfitting in Binary Classification of Gaussian Mixtures
- Blog: On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks
- Blog: Binary Classification Under ℓ0 Attacks for General Noise Distribution
History & citation
Current · Permanent link
- constant-time robust split evaluation split from this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_binary_to_multiclass_generalization_9af158e1,
title = {binary-to-multiclass generalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/binary-to-multiclass-generalization/rdr_9af158e152a844d8af189b91c93a9fc7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_binary_to_multiclass_generalization_9af158e1_v2,
title = {binary-to-multiclass generalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/binary-to-multiclass-generalization/rdr_9af158e152a844d8af189b91c93a9fc7/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}