29 citations · 71 across the 48 of their papers we have counts for
23 papers · 1 filter
Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning
Myoungjun Kim, Sangwoo Park, Yoseob Han +1
Differentially private federated fine-tuning of large models with LoRA suffers from aggregation error caused by LoRA's multiplicative structure, which is further amplified by DP no…
On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization
Prabodh Katti, Houssem Sifaou, Sangwoo Park +2
On-device fine-tuning is a critical capability for edge AI systems, which must support adaptation to different agentic tasks under stringent memory constraints. Conventional backpr…
Reliable Inference in Edge-Cloud Model Cascades via Conformal Alignment
Jiayi Huang, Sangwoo Park, Nicola Paoletti +1
Edge intelligence enables low-latency inference via compact on-device models, but assuring reliability remains challenging. We study edge-cloud cascades that must preserve conditio…
Optimizing In-Context Learning for Efficient Full Conformal Prediction
Weicao Deng, Sangwoo Park, Min Li +1
Reliable uncertainty quantification is critical for trustworthy AI. Conformal Prediction (CP) provides prediction sets with distribution-free coverage guarantees, but its two main…
Reliable Wireless Indoor Localization via Cross-Validated Prediction-Powered Calibration
Seonghoon Yoo, Houssem Sifaou, Sangwoo Park +2
Wireless indoor localization using predictive models with received signal strength information (RSSI) requires proper calibration for reliable position estimates. One remedy is to…
Generalization and Informativeness of Weighted Conformal Risk Control Under Covariate Shift
Matteo Zecchin, Fredrik Hellström, Sangwoo Park +2
Predictive models are often required to produce reliable predictions under statistical conditions that are not matched to the training data. A common type of training-testing misma…
Distilling Calibration via Conformalized Credal Inference
Jiayi Huang, Sangwoo Park, Nicola Paoletti +1
Deploying artificial intelligence (AI) models on edge devices involves a delicate balance between meeting stringent complexity constraints, such as limited memory and energy resour…
Robust Bayesian Optimization via Localized Online Conformal Prediction
Dongwon Kim, Matteo Zecchin, Sangwoo Park +2
Bayesian optimization (BO) is a sequential approach for optimizing black-box objective functions using zeroth-order noisy observations. In BO, Gaussian processes (GPs) are employed…
Automatic AI Model Selection for Wireless Systems: Online Learning via Digital Twinning
Qiushuo Hou, Matteo Zecchin, Sangwoo Park +4
In modern wireless network architectures, such as O-RAN, artificial intelligence (AI)-based applications are deployed at intelligent controllers to carry out functionalities like s…
Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference
Jiayi Huang, Sangwoo Park, Osvaldo Simeone
The application of artificial intelligence (AI) models in fields such as engineering is limited by the known difficulty of quantifying the reliability of an AI's decision. A well-c…
Multi-Fidelity Bayesian Optimization With Across-Task Transferable Max-Value Entropy Search
Yunchuan Zhang, Sangwoo Park, Osvaldo Simeone
In many applications, ranging from logistics to engineering, a designer is faced with a sequence of optimization tasks for which the objectives are in the form of black-box functio…
Generalization and Informativeness of Conformal Prediction
Matteo Zecchin, Sangwoo Park, Osvaldo Simeone +1
The safe integration of machine learning modules in decision-making processes hinges on their ability to quantify uncertainty. A popular technique to achieve this goal is conformal…
Cross-Validation Conformal Risk Control
Kfir M. Cohen, Sangwoo Park, Osvaldo Simeone +1
Conformal risk control (CRC) is a recently proposed technique that applies post-hoc to a conventional point predictor to provide calibration guarantees. Generalizing conformal pred…
Bayesian Optimization with Formal Safety Guarantees via Online Conformal Prediction
Yunchuan Zhang, Sangwoo Park, Osvaldo Simeone
Black-box zero-th order optimization is a central primitive for applications in fields as diverse as finance, physics, and engineering. In a common formulation of this problem, a d…
Calibration-Aware Bayesian Learning
Jiayi Huang, Sangwoo Park, Osvaldo Simeone
Deep learning models, including modern systems like large language models, are well known to offer unreliable estimates of the uncertainty of their decisions. In order to improve t…
Calibrating AI Models for Wireless Communications via Conformal Prediction
Kfir M. Cohen, Sangwoo Park, Osvaldo Simeone +1
When used in complex engineered systems, such as communication networks, artificial intelligence (AI) models should be not only as accurate as possible, but also well calibrated. A…
Fast-Convergent Federated Learning via Cyclic Aggregation
Youngjoon Lee, Sangwoo Park, Joonhyuk Kang
Federated learning (FL) aims at optimizing a shared global model over multiple edge devices without transmitting (private) data to the central server. While it is theoretically wel…
Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance
Youngjoon Lee, Sangwoo Park, Joonhyuk Kang
While being an effective framework of learning a shared model across multiple edge devices, federated learning (FL) is generally vulnerable to Byzantine attacks from adversarial ed…
Learning with Limited Samples -- Meta-Learning and Applications to Communication Systems
Lisha Chen, Sharu Theresa Jose, Ivana Nikoloska +3
Deep learning has achieved remarkable success in many machine learning tasks such as image classification, speech recognition, and game playing. However, these breakthroughs are of…
Continual Meta-Reinforcement Learning for UAV-Aided Vehicular Wireless Networks
Riccardo Marini, Sangwoo Park, Osvaldo Simeone +1
Unmanned aerial base stations (UABSs) can be deployed in vehicular wireless networks to support applications such as extended sensing via vehicle-to-everything (V2X) services. A ke…
Robust Bayesian Learning for Reliable Wireless AI: Framework and Applications
Matteo Zecchin, Sangwoo Park, Osvaldo Simeone +2
This work takes a critical look at the application of conventional machine learning methods to wireless communication problems through the lens of reliability and robustness. Deep…
Robust PAC: Training Ensemble Models Under Misspecification and Outliers
Matteo Zecchin, Sangwoo Park, Osvaldo Simeone +2
Standard Bayesian learning is known to have suboptimal generalization capabilities under misspecification and in the presence of outliers. PAC-Bayes theory demonstrates that the fr…
Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalization
Kfir M. Cohen, Sangwoo Park, Osvaldo Simeone +1
Two of the main principles underlying the life cycle of an artificial intelligence (AI) module in communication networks are adaptation and monitoring. Adaptation refers to the nee…