A Unified Memory Perspective for Probabilistic Trustworthy AI

2026-03-26 · Xueji Zhao, Likai Pei, Jianbo Liu, Kai Ni, Ningyuan Cao arxiv

Trustworthy artificial intelligence increasingly relies on probabilistic computation to achieve robustness, interpretability, security and privacy. In practical systems, such workloads interleave deterministic data access with repeated stochastic sampling across models, data paths and system functions, shifting performance bottlenecks from arithmetic units to memory systems that must deliver both data and randomness. Here we present a unified data-access perspective in which deterministic access is treated as a limiting case of stochastic sampling, enabling both modes to be analyzed within a common framework. This view reveals that increasing stochastic demand reduces effective data-access efficiency and can drive systems into entropy-limited operation. Based on this insight, we define memory-level evaluation criteria, including unified operation, distribution programmability, efficiency, robustness to hardware non-idealities and parallel compatibility. Using these criteria, we analyze limitations of conventional architectures and examine emerging probabilistic compute-in-memory approaches that integrate sampling with memory access, outlining pathways toward scalable hardware for trustworthy AI.

📄 PDF Abstract BibTeX arXiv:2603.25692

Code (0)

등록된 구현이 없습니다.

Probabilistic Robustness in Medical Image Classification

2026-07-04 · Yi Zhang, Siddartha Khastgir, Xingyu Zhao arxiv

Deep learning (DL) has shown strong performance in medical image classification, but its trustworthy deployment remains challenging in safety-critical clinical settings, where prediction errors under perturbations may le…

Medical Image Classification Adversarial Robustness

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

2022-09-16 · Mengdi Xu, Zuxin Liu, Peide Huang, Wenhao Ding 외

A trustworthy reinforcement learning algorithm should be competent in solving challenging real-world problems, including {robustly} handling uncertainties, satisfying {safety} constraints to avoid catastrophic failures, …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

ReasonOps: A Unified Operational Paradigm for Trustworthy Verified LLM Reasoning

2026-05-26 · Adnan Rashid arxiv

Large Language Models (LLMs) have transformed artificial intelligence from primarily generative systems into increasingly capable reasoning agents. Recent advances in theorem proving, autoformalization, symbolic reasonin…

Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives

2023-07-31 · Haoyang Liu, Maheep Chaudhary, Haohan Wang

The trustworthiness of machine learning has emerged as a critical topic in the field, encompassing various applications and research areas such as robustness, security, interpretability, and fairness. The last decade saw…

Adversarial Robustness Fairness parameter-efficient fine-tuning Survey

Foundations of Reliable Inference: Reliability-Efficiency Co-Design

2026-05-11 · Jiayi Huang arxiv

Reliable inference requires that artificial intelligence (AI) models provide trustworthy uncertainty estimates, not merely accurate predictions. Recent advances in Bayesian learning have made significant progress toward …