Stress-Aware Learning under KL Drift via Trust-Decayed Mirror Descent
We study sequential decision-making under distribution drift. We propose entropy-regularized trust-decay, which injects stress-aware exponential tilting into both belief updates and mirror-descent decisions. On the simplex, a Fenchel-dual equivalence shows that belief tilt and decision tilt coincide. We formalize robustness via fragility (worst-case excess risk in a KL ball), belief bandwidth (radius sustaining a target excess), and a decision-space Fragility Index (drift tolerated at $O(\sqrt{T})$ regret). We prove high-probability sensitivity bounds and establish dynamic-regret guarantees of $\tilde{O}(\sqrt{T})$ under KL-drift path length $S_T = \sum_{t\ge2}\sqrt{{\rm KL}(D_t|D_{t-1})/2}$. In particular, trust-decay achieves $O(1)$ per-switch regret, while stress-free updates incur $Ω(1)$ tails. A parameter-free hedge adapts the tilt to unknown drift, whereas persistent over-tilting yields an $Ω(λ^2 T)$ stationary penalty. We further obtain calibrated-stress bounds and extensions to second-order updates, bandit feedback, outliers, stress variation, distributed optimization, and plug-in KL-drift estimation. The framework unifies dynamic-regret analysis, distributionally robust objectives, and KL-regularized control within a single stress-adaptive update.
Code (0)
등록된 구현이 없습니다.
Tasks
Distributed OptimizationSimilar Papers 제목 키워드 기반
DAO-GP Drift Aware Online Non-Linear Regression Gaussian-Process
Real-world datasets often exhibit temporal dynamics characterized by evolving data distributions. Disregarding this phenomenon, commonly referred to as concept drift, can significantly diminish a model's predictive accur…
Adversarial Moral Stress Testing of Large Language Models
Evaluating the ethical robustness of large language models (LLMs) deployed in software systems remains challenging, particularly under sustained adversarial user interaction. Existing safety benchmarks typically rely on …
Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization
Big-Data-as-a-Service (BDaaS) platforms require re liable automation across data ingestion, cleaning, feature engi neering, model development, deployment, and post-deployment monitoring. However, existing LLM-based data …
Feature EngineeringCADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift
Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as an accuracy one. Updating a deployed model for a new imaging modality ca…
Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration
To facilitate a wide-spread acceptance of AI systems guiding decision making in real-world applications, trustworthiness of deployed models is key. That is, it is crucial for predictive models to be uncertainty-aware and…
Decision Making