Non-quadratic Mirror Descent exhibits exponential initialization sensitivity in convex settings, shown via 3D constructions and KL-regularized simplex examples, with Bregman anchoring proposed for stabilization.
Title resolution pending
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
Fuzzy ARTMAP models are highly vulnerable to a new white-box attack aligned with their category competition, but progressive selective training yields stronger replay-free robustness than offline adversarial training under adaptive evaluation.
Continual classification in homogeneous models is sequential projections onto margin sets, with local linear convergence under regularity properties for random and cyclic tasks, extended to regression.
RoHIL adapts human-in-the-loop RL policies to new illumination conditions offline by combining world-model image relighting, illumination-retention replay, and anchored Bellman regularisation, improving shifted-light performance while preserving source performance on four real-robot tasks.
TaskFusion combines AGF feature mapping, cross-task augmentation, and distilled replay for continual anomaly detection on heterogeneous tabular data, reporting gains over baselines on 21 datasets.
NoFA-BC proposes a non-forgetting allocator using recursive least-squares and bi-level competition for improved knowledge allocation in class-incremental learning.
TRACER applies weighted moving average distillation in contrastive finetuning of multimodal models to retain pretrained knowledge and boost out-of-distribution accuracy.
Integrates SAM-Audio dense representations with guided attention and dual distillation for audio-visual class-incremental learning, reporting consistent outperformance on benchmarks.
citing papers explorer
-
Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity
Non-quadratic Mirror Descent exhibits exponential initialization sensitivity in convex settings, shown via 3D constructions and KL-regularized simplex examples, with Bregman anchoring proposed for stabilization.
-
Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics
Fuzzy ARTMAP models are highly vulnerable to a new white-box attack aligned with their category competition, but progressive selective training yields stronger replay-free robustness than offline adversarial training under adaptive evaluation.