Algorithmic Stability

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 35

All topics

CCAR: Intrinsic Robustness as an Emergent Geometric Property
Apr 18, 2026Akash Samanta, Manish Pratap Singh, Debasis ChaudhuriDisentangled Representation Learning Representation Learning
Techno India University, Salt Lake, Kolkata, India · DRDO Young Scientist Laboratory - CT, Chennai, India
The Impact of Dimensionality on the Stability of Node Embeddings
Apr 9, 2026Tobias Schumacher, Simon Reichelt, Markus StrohmaierRepresentation Learning Algorithmic Stability
University of Mannheim · RWTH Aachen University · GESIS - Leibniz Institute for the Social Sciences, and +1
Jacobian-Adaptive Weighting for Stability: Enhancing Long-term Rollout of Neural Partial Differential Equation Solvers via Spatially-Adaptive Regularization
Mar 4, 2026Fengxiang Nie, Yasuhiro SuzukiNeural PDE Solvers Algorithmic Stability
University of Hiroshima
Learnable Mixed Nash Equilibria are Collectively Rational
Oct 16, 2025Geelon So, Yi-An MaNash Equilibrium Algorithmic Stability
University of California, San Diego
Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning
Jun 22, 2025Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1Byzantine-Robust Federated Learning Algorithmic Stability
PreMeDICaL team, Inria, Idesp, Inserm, Université de Montpellier, Montpellier, France · Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189, CRIStAL, F-59000 Lille, France · Department of Computer Science, University of Copenhagen, Copenhagen, Danemark

Apr 18, 2026, cs.LGJ/K move · Enter open · S save

CCAR: Intrinsic Robustness as an Emergent Geometric Property

Akash Samanta, Manish Pratap Singh, Debasis Chaudhuri

Techno India University, Salt Lake, Kolkata, India · DRDO Young Scientist Laboratory - CT, Chennai, India

Disentangled Representation Learning Representation Learning Algorithmic Stability Neural Network Robustness Adversarial Robustness Orthogonal Representation Learning+2

Open paper AskPDF arXiv

Standard supervised learning optimizes for predictive accuracy but remains agnostic to the internal geometry of learned features, often yielding representations that are entangled and brittle. We propose Class-Conditional Activation Regularization (CCAR) to explicitly engineer the feature space, imposing a block-diagonal structure via a soft inductive bias. By shaping the latent representation to confine class energy to orthogonal subspaces, we create an intrinsic geometric scaffold that naturally filters noise and adversarial perturbations. We provide theoretical analysis linking this structural constraint to the maximization of the Fisher Discriminant Ratio, establishing a formal connection between geometric disentanglement and algorithmic stability. Empirically, this approach demonstrates that robustness is an emergent property of a well-engineered feature space, significantly outperforming baselines on label noise and input corruption benchmarks.

Momentum

Related topics

Latest papers 35

CCAR: Intrinsic Robustness as an Emergent Geometric Property

The Impact of Dimensionality on the Stability of Node Embeddings

Jacobian-Adaptive Weighting for Stability: Enhancing Long-term Rollout of Neural Partial Differential Equation Solvers via Spatially-Adaptive Regularization

Learnable Mixed Nash Equilibria are Collectively Rational

Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning