@inproceedings{swamyIntrinsicUserCentricInterpretability2024,
	title = {Intrinsic User-Centric Interpretability through Global Mixture of Experts},
	url = {https://openreview.net/forum?id=wDcunIOAOk},
	abstract = {In human-centric settings like education or healthcare, model accuracy and model explainability are key factors for user adoption. Towards these two goals, intrinsically interpretable deep learning models have gained popularity, focusing on accurate predictions alongside faithful explanations. However, there exists a gap in the human-centeredness of these approaches, which often produce nuanced and complex explanations that are not easily actionable for downstream users. We present {InterpretCC} (interpretable conditional computation), a family of intrinsically interpretable neural networks at a unique point in the design space that optimizes for ease of human understanding and explanation faithfulness, while maintaining comparable performance to state-of-the-art models. {InterpretCC} achieves this through adaptive sparse activation of features before prediction, allowing the model to use a different, minimal set of features for each instance. We extend this idea into an interpretable, global mixture-of-experts ({MoE}) model that allows users to specify topics of interest, discretely separates the feature space for each data point into topical subnetworks, and adaptively and sparsely activates these topical subnetworks for prediction. We apply {InterpretCC} for text, time series and tabular data across several real-world datasets, demonstrating comparable performance with non-interpretable baselines and outperforming intrinsically interpretable baselines. Through a user study involving 56 teachers, {InterpretCC} explanations are found to have higher actionability and usefulness over other intrinsically interpretable approaches.},
	eventtitle = {The Thirteenth International Conference on Learning Representations},
	author = {Swamy, Vinitra and Montariol, Syrielle and Blackwell, Julian and Frej, Jibril and Jaggi, Martin and Käser, Tanja},
	urldate = {2025-05-19},
	date = {2024-10-04},
	langid = {english},
}

@article{edingerVacuumsealedSiliconPhotonic2023,
	title = {Vacuum-sealed silicon photonic {MEMS} tunable ring resonator with an independent control over coupling and phase},
	volume = {31},
	issn = {1094-4087},
	url = {https://opg.optica.org/abstract.cfm?URI=oe-31-4-6540},
	doi = {10.1364/OE.480219},
	abstract = {Ring resonators are a vital element for filters, optical delay lines, or sensors in silicon photonics. However, reconfigurable ring resonators with low-power consumption are not available in foundries today. We demonstrate an add-drop ring resonator with the independent tuning of round-trip phase and coupling using low-power microelectromechanical ({MEMS}) actuation. At a wavelength of 1540 nm and for a maximum voltage of 40 V, the phase shifters provide a resonance wavelength tuning of 0.15 nm, while the tunable couplers can tune the optical resonance extinction ratio at the through port from 0 to 30 {dB}. The optical resonance displays a passive quality factor of 29 000, which can be increased to almost 50 000 with actuation. The {MEMS} rings are individually vacuum-sealed on wafer scale, enabling reliable and long-term protection from the environment. We cycled the mechanical actuators for more than 4 × 10
              9
              cycles at 100 {kHz}, and did not observe degradation in their response curves. On mechanical resonance, we demonstrate a modulation increase of up to 15 {dB}, with a voltage bias of 4 V and a peak drive amplitude as low as 20 {mV}.},
	pages = {6540},
	number = {4},
	journaltitle = {Optics Express},
	shortjournal = {Opt. Express},
	author = {Edinger, Pierre and Jo, Gaehun and Van Nguyen, Chris Phong and Takabayashi, Alain Yuji and Errando-Herranz, Carlos and Antony, Cleitus and Talli, Giuseppe and Verheyen, Peter and Khan, Umar and Bleiker, Simon J. and Bogaerts, Wim and Quack, Niels and Niklaus, Frank and Gylfason, Kristinn B.},
	urldate = {2025-03-31},
	date = {2023-02-13},
	langid = {english},
}

@article{sprungerPHQuantificationHuman2023,
	title = {{pH} Quantification in Human Dermal Interstitial Fluid Using Ultra-Thin {SOI} Silicon Nanowire {ISFETs} and a High-Sensitivity Constant-Current Approach},
	volume = {13},
	rights = {https://creativecommons.org/licenses/by/4.0/},
	issn = {2079-6374},
	url = {https://www.mdpi.com/2079-6374/13/10/908},
	doi = {10.3390/bios13100908},
	abstract = {In this paper, we propose a novel approach to utilize silicon nanowires as high-sensitivity {pH} sensors. Our approach works based on fixing the current bias of silicon nanowires Ion Sensitive Field Effect Transistors ({ISFETs}) and monitor the resulting drain voltage as the sensing signal. By fine tuning the injected current levels, we can optimize the sensing conditions according to different sensor requirements. This method proves to be highly suitable for real-time and continuous measurements of biomarkers in human biofluids. To validate our approach, we conducted experiments, with real human sera samples to simulate the composition of human interstitial fluid ({ISF}), using both the conventional top-gate approach and the optimized constant current method. We successfully demonstrated {pH} sensing within the physiopathological range of 6.5 to 8, achieving an exceptional level of accuracy in this complex matrix. Specifically, we obtained a maximum error as low as 0.92\% (equivalent to 0.07 {pH} unit) using the constant-current method at the optimal current levels (1.71\% for top-gate). Moreover, by utilizing different pools of human sera with varying total protein content, we demonstrated that the protein content among patients does not impact the sensors’ performance in {pH} sensing. Furthermore, we tested real-human {ISF} samples collected from volunteers. The obtained accuracy in this scenario was also outstanding, with an error as low as 0.015 {pH} unit using the constant-current method and 0.178 {pH} unit in traditional top-gate configuration.},
	pages = {908},
	number = {10},
	journaltitle = {Biosensors},
	shortjournal = {Biosensors},
	author = {Sprunger, Yann and Capua, Luca and Ernst, Thomas and Barraud, Sylvain and Locca, Didier and Ionescu, Adrian and Saeidi, Ali},
	urldate = {2024-05-15},
	date = {2023-09-27},
	langid = {english},
}

@inproceedings{yakymetsModelBasedISO149712023,
	location = {Sydney, Australia},
	title = {Model-Based {ISO} 14971 Risk Management of {EEG}-Based Medical Devices},
	rights = {https://doi.org/10.15223/policy-029},
	isbn = {979-8-3503-2447-1},
	url = {https://ieeexplore.ieee.org/document/10340131/},
	doi = {10.1109/EMBC40787.2023.10340131},
	eventtitle = {2023 45th Annual International Conference of the {IEEE} Engineering in Medicine \& Biology Society ({EMBC})},
	pages = {1--7},
	booktitle = {2023 45th Annual International Conference of the {IEEE} Engineering in Medicine \& Biology Society ({EMBC})},
	publisher = {{IEEE}},
	author = {Yakymets, N. and Zanetti, R. and Ionescu, A. and Atienza, D.},
	urldate = {2024-05-15},
	date = {2023-07-24},
}

@article{karamiTimEHRImagebasedTime2025,
	title = {{TimEHR}: Image-based Time Series Generation for Electronic Health Records},
	rights = {https://creativecommons.org/licenses/by/4.0/legalcode},
	issn = {2168-2194, 2168-2208},
	url = {https://ieeexplore.ieee.org/document/11027528/},
	doi = {10.1109/JBHI.2025.3577328},
	shorttitle = {{TimEHR}},
	pages = {1--12},
	journaltitle = {{IEEE} Journal of Biomedical and Health Informatics},
	shortjournal = {{IEEE} J. Biomed. Health Inform.},
	eprinttype = {arxiv},
	eprint = {https://arxiv.org/abs/2402.06318},
	author = {Karami, Hojjat and Hartley, Mary-Anne and Atienza, David and Ionescu, Anisoara},
	urldate = {2025-08-30},
	date = {2025},
}

@inproceedings{sprungerUltraHighSensitivitySilicon2023,
	location = {Lisbon, Portugal},
	title = {Ultra-High Sensitivity Silicon Nanowire Array Biosensor Based on a Constant-Current Method for Continuous Real-Time {pH} and Protein Monitoring in Interstitial Fluid},
	isbn = {979-8-3503-0420-6},
	url = {https://ieeexplore.ieee.org/document/10268731/},
	doi = {10.1109/ESSCIRC59616.2023.10268731},
	eventtitle = {{ESSCIRC} 2023- {IEEE} 49th European Solid State Circuits Conference ({ESSCIRC})},
	pages = {153--156},
	booktitle = {{ESSCIRC} 2023- {IEEE} 49th European Solid State Circuits Conference ({ESSCIRC})},
	publisher = {{IEEE}},
	author = {Sprunger, Y. and Capua, L. and Ernst, T. and Barraud, S. and Ionescu, A.M. and Saeidi, A.},
	urldate = {2023-12-07},
	date = {2023-09-11},
}

@article{renlundUseSiliconMicroneedle2025,
	title = {Use of a Silicon Microneedle Chip-Based Device for the Extraction and Subsequent Analysis of Dermal Interstitial Fluid in Heart Failure Patients},
	volume = {15},
	rights = {https://creativecommons.org/licenses/by/4.0/},
	issn = {2075-4418},
	url = {https://www.mdpi.com/2075-4418/15/8/989},
	doi = {10.3390/diagnostics15080989},
	abstract = {Background/Objectives: Dermal interstitial fluid ({dISF}) is probably the most interesting biofluid for biomarker analysis as an alternative to blood, enabling higher patient comfort and closer or even continuous biomarker monitoring. The prerequisite for {dISF}-based analysis tools is having convenient access to {dISF}, as well as a better knowledge of the presence, concentration, and dynamics of biomarkers in {dISF}. Hollow microneedles represent one of the most promising platforms for access to pure {dISF}, enabling the mining of biomarker information. Methods and Results: Here, a microneedle-based method for {dISF} sampling is presented, where a combination of hollow microneedles and sub-pressure is used to optimize both penetration depth in skin and dermal interstitial fluid sampling volumes, and the design of an open, prospective, exploratory, and interventional study to examine the detectability of inflammatory and cardiocirculatory biomarkers in the {dISF} of heart failure patients, the relationship between {dISF}-derived and blood-derived biomarker levels, and their kinetics during a cardiopulmonary exercise test ({CPET}) is introduced. Conclusions: The {dISF} sampling method and study presented here will foster research on biomarkers in {dISF} in general and in heart failure patients in particular. The study is part of the European project {DIGIPREDICT}—Digital Edge {AI}-deployed {DIGItal} Twins for {PREDICTing} disease progression and the need for early intervention in infectious and cardiovascular diseases beyond {COVID}-19.},
	pages = {989},
	number = {8},
	journaltitle = {Diagnostics},
	shortjournal = {Diagnostics},
	author = {Renlund, Markus and Kopp Fernandes, Laurenz and Rangsten, Pelle and Hillmering, Mikael and Mosel, Sara and Issa, Ziad and Falk, Volkmar and Meyer, Alexander and Schoenrath, Felix},
	urldate = {2025-04-23},
	date = {2025-04-13},
	langid = {english},
}

@inproceedings{zakharovaIntegratedSiliconOnInsulatorBased2024,
	location = {Kobe, Japan},
	title = {Integrated Silicon-On-Insulator Based Mesh Membrane for Continuous Monitoring in Organs-on-a-chip},
	rights = {https://doi.org/10.15223/policy-029},
	isbn = {979-8-3503-6351-7},
	url = {https://ieeexplore.ieee.org/document/10784460/},
	doi = {10.1109/SENSORS60989.2024.10784460},
	eventtitle = {2024 {IEEE} {SENSORS}},
	pages = {1--4},
	booktitle = {2024 {IEEE} {SENSORS}},
	publisher = {{IEEE}},
	author = {Zakharova, Mariia and Cóndor, Mar and Shaikh, Sohail F. and Delahanty, Aaron and Braeken, Dries and Van Der Meer, Andries D. and Segerink, Loes I.},
	urldate = {2025-04-15},
	date = {2024-10-20},
}

@inproceedings{karamiPointprocessbasedRepresentationLearning2023,
	location = {Pittsburgh, {PA}, {USA}},
	title = {Point-process-based Representation Learning for Electronic Health Records},
	isbn = {979-8-3503-1050-4},
	url = {https://ieeexplore.ieee.org/document/10313499/},
	doi = {10.1109/BHI58575.2023.10313499},
	eventtitle = {2023 {IEEE} {EMBS} International Conference on Biomedical and Health Informatics ({BHI})},
	pages = {1--4},
	booktitle = {2023 {IEEE} {EMBS} International Conference on Biomedical and Health Informatics ({BHI})},
	publisher = {{IEEE}},
	author = {Karami, Hojjat and Ionescu, Anisoara and Atienza, David},
	urldate = {2023-12-07},
	date = {2023-10-15},
}

@inproceedings{orlandicHowCountCoughs2024a,
	location = {Chicago, {IL}, {USA}},
	title = {How to Count Coughs: An Event-Based Framework for Evaluating Automatic Cough Detection Algorithm Performance},
	rights = {https://doi.org/10.15223/policy-029},
	isbn = {979-8-3315-3014-3},
	url = {https://ieeexplore.ieee.org/document/10780617/},
	doi = {10.1109/BSN63547.2024.10780617},
	shorttitle = {How to Count Coughs},
	eventtitle = {2024 {IEEE} 20th International Conference on Body Sensor Networks ({BSN})},
	pages = {1--4},
	booktitle = {2024 {IEEE} 20th International Conference on Body Sensor Networks ({BSN})},
	publisher = {{IEEE}},
	eprinttype = {arxiv},
	eprint = {https://arxiv.org/abs/2406.01529},
	author = {Orlandic, Lara and Dan, Jonathan and Thevenot, Jérôme and Teijeiro, Tomas and Sauty, Alain and Atienza, David},
	urldate = {2025-01-17},
	date = {2024-10-15},
}

@article{karamiTEE4EHRTransformerEvent2024,
	title = {{TEE}4EHR: Transformer event encoder for better representation learning in electronic health records},
	volume = {154},
	issn = {09333657},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0933365724001453},
	doi = {10.1016/j.artmed.2024.102903},
	shorttitle = {{TEE}4EHR},
	pages = {102903},
	journaltitle = {Artificial Intelligence in Medicine},
	shortjournal = {Artificial Intelligence in Medicine},
	eprinttype = {arxiv},
	eprint = {https://arxiv.org/abs/2402.06367},
	author = {Karami, Hojjat and Atienza, David and Ionescu, Anisoara},
	urldate = {2024-11-26},
	date = {2024-08},
	langid = {english},
}

@inproceedings{vollmannTunableDualMode2024,
	location = {Austin, {TX}, {USA}},
	title = {Tunable Dual Mode Carbon Nanotube Strain Gauge},
	rights = {https://doi.org/10.15223/policy-029},
	isbn = {979-8-3503-5792-9},
	url = {https://ieeexplore.ieee.org/document/10439427/},
	doi = {10.1109/MEMS58180.2024.10439427},
	eventtitle = {2024 {IEEE} 37th International Conference on Micro Electro Mechanical Systems ({MEMS})},
	pages = {931--934},
	booktitle = {2024 {IEEE} 37th International Conference on Micro Electro Mechanical Systems ({MEMS})},
	publisher = {{IEEE}},
	author = {Vollmann, Morten and Roman, Cosmin and Hierold, Christofer},
	urldate = {2024-11-26},
	date = {2024-01-21},
}

@article{linMultichannelElectrochemicalSensor2023,
	title = {A Multichannel Electrochemical Sensor Interface {IC} for Bioreactor Monitoring},
	issn = {1932-4545, 1940-9990},
	url = {https://ieeexplore.ieee.org/document/10251576/},
	doi = {10.1109/TBCAS.2023.3315480},
	pages = {1--9},
	journaltitle = {{IEEE} Transactions on Biomedical Circuits and Systems},
	shortjournal = {{IEEE} Trans. Biomed. Circuits Syst.},
	author = {Lin, Qiuyang and Sijbers, Wim and Avdikou, Christina and Gomez, Didac and Biswas, Dwaipayan and Tacca, Bernardo and Van Helleputte, Nick},
	urldate = {2023-09-28},
	date = {2023},
}

@inproceedings{orlandicMultimodalDatasetAutomatic2023,
	title = {A Multimodal Dataset for Automatic Edge-{AI} Cough Detection},
	rights = {Creative Commons Attribution 4.0 International, Open Access},
	url = {https://zenodo.org/record/7562332},
	doi = {10.5281/ZENODO.7562332},
	abstract = {Counting the number of times a patient coughs per day is an essential biomarker in determining treatment efficacy for novel antitussive therapies and personalizing patient care. There is a need for wearable devices that employ multimodal sensors to perform accurate, privacy-preserving, automatic cough counting algorithms directly on the device in an edge-{AI} fashion. To advance this research field, we contribute the first publicly accessible cough counting dataset of multimodal biosignals. The database contains nearly 4 hours of biosignal data, with both acoustic and kinematic modalities, covering 4,300 annotated cough events. Furthermore, several non-cough sounds (i.e. breathing, laughing, and throat clearing), background noises (i.e. music, traffic, bystander coughing) and motion scenarios (i.e. sitting, walking) mimicking daily life activities are also present, which the research community can use to accelerate {ML} algorithm development. For detailed information about using this dataset to train edge-{AI} models and example code, please refer to our public Git repository: https://github.com/esl-epfl/edge-ai-cough-count/},
	publisher = {{IEEE}},
	author = {Orlandic, Lara and Thevenot, Jérôme and Teijeiro, Tomas and Atienza, David},
	urldate = {2023-09-28},
	date = {2023-01-23},
	keywords = {automatic cough detection, edge-{AI}, multimodal biosignals},
}

@article{orlandicSemisupervisedAlgorithmImproving2023,
	title = {A semi-supervised algorithm for improving the consistency of crowdsourced datasets: The {COVID}-19 case study on respiratory disorder classification},
	volume = {241},
	issn = {01692607},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0169260723004091},
	doi = {10.1016/j.cmpb.2023.107743},
	shorttitle = {A semi-supervised algorithm for improving the consistency of crowdsourced datasets},
	pages = {107743},
	journaltitle = {Computer Methods and Programs in Biomedicine},
	shortjournal = {Computer Methods and Programs in Biomedicine},
	eprinttype = {arxiv},
	eprint = {https://arxiv.org/pdf/2209.04360.pdf},
	author = {Orlandic, Lara and Teijeiro, Tomas and Atienza, David},
	urldate = {2023-08-21},
	date = {2023-11},
	langid = {english},
}

@article{zanoliEventbasedSampledECG2023,
	title = {Event-based sampled {ECG} morphology reconstruction through self-similarity},
	volume = {240},
	issn = {01692607},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0169260723003784},
	doi = {10.1016/j.cmpb.2023.107712},
	pages = {107712},
	journaltitle = {Computer Methods and Programs in Biomedicine},
	shortjournal = {Computer Methods and Programs in Biomedicine},
	eprinttype = {arxiv},
	eprint = {https://arxiv.org/abs/2207.01856},
	author = {Zanoli, Silvio and Ansaloni, Giovanni and Teijeiro, Tomás and Atienza, David},
	urldate = {2023-07-13},
	date = {2023-10},
	langid = {english},
}

@article{zanoliErrorBasedApproximationSensing2023,
	title = {An Error-Based Approximation Sensing Circuit for Event-Triggered Low-Power Wearable Sensors},
	volume = {13},
	issn = {2156-3357, 2156-3365},
	url = {https://ieeexplore.ieee.org/document/10107413/},
	doi = {10.1109/JETCAS.2023.3269623},
	pages = {489--501},
	number = {2},
	journaltitle = {{IEEE} Journal on Emerging and Selected Topics in Circuits and Systems},
	shortjournal = {{IEEE} J. Emerg. Sel. Topics Circuits Syst.},
	eprinttype = {arxiv},
	eprint = {https://arxiv.org/abs/2106.13545},
	author = {Zanoli, Silvio and Ponzina, Flavio and Teijeiro, Tomás and Levisse, Alexandre and Atienza, David},
	urldate = {2023-07-06},
	date = {2023-06},
}

@article{buttiaPrognosticModelsCOVID192023,
	title = {Prognostic models in {COVID}-19 infection that predict severity: a systematic review},
	issn = {0393-2990, 1573-7284},
	url = {https://link.springer.com/10.1007/s10654-023-00973-x},
	doi = {10.1007/s10654-023-00973-x},
	shorttitle = {Prognostic models in {COVID}-19 infection that predict severity},
	abstract = {Abstract
            Current evidence on {COVID}-19 prognostic models is inconsistent and clinical applicability remains controversial. We performed a systematic review to summarize and critically appraise the available studies that have developed, assessed and/or validated prognostic models of {COVID}-19 predicting health outcomes. We searched six bibliographic databases to identify published articles that investigated univariable and multivariable prognostic models predicting adverse outcomes in adult {COVID}-19 patients, including intensive care unit ({ICU}) admission, intubation, high-flow nasal therapy ({HFNT}), extracorporeal membrane oxygenation ({ECMO}) and mortality. We identified and assessed 314 eligible articles from more than 40 countries, with 152 of these studies presenting mortality, 66 progression to severe or critical illness, 35 mortality and {ICU} admission combined, 17 {ICU} admission only, while the remaining 44 studies reported prediction models for mechanical ventilation ({MV}) or a combination of multiple outcomes. The sample size of included studies varied from 11 to 7,704,171 participants, with a mean age ranging from 18 to 93 years. There were 353 prognostic models investigated, with area under the curve ({AUC}) ranging from 0.44 to 0.99. A great proportion of studies (61.5\%, 193 out of 314) performed internal or external validation or replication. In 312 (99.4\%) studies, prognostic models were reported to be at high risk of bias due to uncertainties and challenges surrounding methodological rigor, sampling, handling of missing data, failure to deal with overfitting and heterogeneous definitions of {COVID}-19 and severity outcomes. While several clinical prognostic models for {COVID}-19 have been described in the literature, they are limited in generalizability and/or applicability due to deficiencies in addressing fundamental statistical and methodological concerns. Future large, multi-centric and well-designed prognostic prospective studies are needed to clarify remaining uncertainties.},
	journaltitle = {European Journal of Epidemiology},
	shortjournal = {Eur J Epidemiol},
	author = {Buttia, Chepkoech and Llanaj, Erand and Raeisi-Dehkordi, Hamidreza and Kastrati, Lum and Amiri, Mojgan and Meçani, Renald and Taneri, Petek Eylul and Ochoa, Sergio Alejandro Gómez and Raguindin, Peter Francis and Wehrli, Faina and Khatami, Farnaz and Espínola, Octavio Pano and Rojas, Lyda Z. and de Mortanges, Aurélie Pahud and Macharia-Nimietz, Eric Francis and Alijla, Fadi and Minder, Beatrice and Leichtle, Alexander B. and Lüthi, Nora and Ehrhard, Simone and Que, Yok-Ai and Fernandes, Laurenz Kopp and Hautz, Wolf and Muka, Taulant},
	urldate = {2023-03-09},
	date = {2023-02-25},
	langid = {english},
}

@inproceedings{capuaDoubleGateSiNanowire2021,
	location = {San Francisco, {CA}, {USA}},
	title = {Double-Gate Si Nanowire {FET} Sensor Arrays For Label-Free C-Reactive Protein detection enabled by antibodies fragments and pseudo-super-Nernstian back-gate operation},
	isbn = {978-1-6654-2572-8},
	url = {https://ieeexplore.ieee.org/document/9720670/},
	doi = {10.1109/IEDM19574.2021.9720670},
	eventtitle = {2021 {IEEE} International Electron Devices Meeting ({IEDM})},
	pages = {16.2.1--16.2.4},
	booktitle = {2021 {IEEE} International Electron Devices Meeting ({IEDM})},
	publisher = {{IEEE}},
	author = {Capua, L. and Sprunger, Y. and Elettro, H. and Grammoustianou, A. and Midahuen, R. and Ernst, T. and Barraud, S. and Gill, R. and Ionescu, A.M.},
	urldate = {2022-05-19},
	date = {2021-12-11},
}

@inproceedings{koloskovaImprovedAnalysisGradient2021,
	title = {An Improved Analysis of Gradient Tracking for Decentralized Machine Learning},
	volume = {34},
	isbn = {978-1-7138-4539-3},
	url = {https://proceedings.neurips.cc/paper/2021/hash/5f25fbe144e4a81a1b0080b6c1032778-Abstract.html},
	series = {{NeurIPS} Proceedings},
	eventtitle = {Thirty-fifth Conference on Neural Information Processing Systems ({NeurIPS} 202)},
	booktitle = {Advances in Neural Information Processing Systems},
	publisher = {{NIPS}},
	eprinttype = {arxiv},
	eprint = {https://arxiv.org/abs/2202.03836},
	author = {Koloskova, Anastasiia and Lin, Tao and Stich, Sebastian U.},
	urldate = {2022-02-23},
	date = {2021-12-06},
	langid = {english},
}

@inproceedings{kongConsensusControlDecentralized2021,
	title = {Consensus Control for Decentralized Deep Learning},
	volume = {139},
	url = {https://proceedings.mlr.press/v139/kong21a.html},
	series = {Proceedings of Machine Learning Research},
	abstract = {Decentralized training of deep learning models enables on-device learning over networks, as well as efficient scaling to large compute clusters. Experiments in earlier works reveal that, even in a data-center setup, decentralized training often suffers from the degradation in the quality of the model: the training and test performance of models trained in a decentralized fashion is in general worse than that of models trained in a centralized fashion, and this performance drop is impacted by parameters such as network size, communication topology and data partitioning.},
	eventtitle = {38th International Conference on Machine Learning ({ICML})},
	pages = {5686--5696},
	booktitle = {Proceedings of the 38th International Conference on Machine Learning},
	publisher = {{PMLR}},
	eprinttype = {arxiv},
	eprint = {https://arxiv.org/abs/2102.04828},
	author = {Kong, Lingjing and Lin, Tao and Koloskova, Anastasia and Jaggi, Martin and Stich, Sebastian U},
	date = {2021},
	langid = {english},
}

@inproceedings{vogelsRelaySumDecentralizedDeep2021,
	title = {{RelaySum} for Decentralized Deep Learning on Heterogeneous Data},
	volume = {34},
	url = {https://proceedings.neurips.cc/paper/2021/hash/ebbdfea212e3a756a1fded7b35578525-Abstract.html},
	series = {{NeurIPS} Proceedings},
	eventtitle = {Thirty-fifth Conference on Neural Information Processing Systems ({NeurIPS} 202)},
	booktitle = {Advances in Neural Information Processing Systems},
	publisher = {{NIPS}},
	eprinttype = {arxiv},
	eprint = {https://arxiv.org/abs/2110.04175},
	author = {Vogels, Thijs and He, Lie and Koloskova, Anastasiia and Karimireddy, Sai Praneeth and Lin, Tao and Stich, Sebastian U. and Jaggi, Martin},
	urldate = {2022-02-23},
	date = {2021-12-06},
	langid = {english},
}

@article{capuaLabelFreeCReactiveProtein2022,
	title = {Label-Free C-Reactive Protein Si Nanowire {FET} Sensor Arrays With Super-Nernstian Back-Gate Operation},
	issn = {0018-9383, 1557-9646},
	url = {https://ieeexplore.ieee.org/document/9709497/},
	doi = {10.1109/TED.2022.3144108},
	pages = {1--7},
	journaltitle = {{IEEE} Transactions on Electron Devices},
	shortjournal = {{IEEE} Trans. Electron Devices},
	author = {Capua, Luca and Sprunger, Yann and Elettro, H. and Risch, F. and Grammoustianou, A. and Midahuen, R. and Ernst, T. and Barraud, S. and Gill, R. and Ionescu, A. M.},
	urldate = {2022-02-16},
	date = {2022},
	keywords = {peer-reviewed},
}

@inproceedings{linQuasiGlobalMomentumAccelerating2021,
	title = {Quasi-Global Momentum:  Accelerating Decentralized Deep Learning on Heterogeneous Data},
	volume = {139},
	url = {https://proceedings.mlr.press/v139/lin21c.html},
	series = {Proceedings of Machine Learning Research},
	abstract = {Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients’ local datasets poses an optimization challenge and may severely deteriorate the generalization performance. In this paper, we investigate and identify the limitation of several decentralized optimization algorithms for different degrees of data heterogeneity. We propose a novel momentum-based method to mitigate this decentralized training difficulty. We show in extensive empirical experiments on various {CV}/{NLP} datasets ({CIFAR}-10, {ImageNet}, and {AG} News) and several network topologies (Ring and Social Network) that our method is much more robust to the heterogeneity of clients’ data than other existing methods, by a significant improvement in test performance (1\%−20\%). Our code is publicly available1.},
	eventtitle = {38th International Conference on Machine Learning ({ICML})},
	pages = {6654--6665},
	booktitle = {Proceedings of the 38th International Conference on Machine Learning},
	publisher = {{PMLR}},
	author = {Lin, Tao and Karimireddy, Sai Praneeth and Stich, Sebastian U and Jaggi, Martin},
	date = {2021},
	langid = {english},
}