Theses
U. Şimşekli, “Tensor Fusion: Learning In Heterogeneous and Distributed Data”, PhD Thesis, Boğaziçi University, Istanbul, Turkey, 2015
U. Şimşekli, "Bayesian Methods for Real-Time Pitch Tracking", MS Thesis, Boğaziçi University, Istanbul, Turkey, 2010
Patents
J. Le Roux, J. R. Hershey, U. Şimşekli, “Denoising Noisy Speech Signals Using Probabilistic Model”, US Patent, 2014
Publications on Machine Learning Methodology/Theory
Working papers/Preprints
U. Simsekli, M. Gurbuzbalaban, S. Yildirim, L. Zhu, "Differential Privacy of Noisy (S) GD under Heavy-Tailed Perturbations", arXiv, 2024
B. Dupuis, U. Simsekli, "Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation", arXiv, 2024
F. Schaipp, G. Garrigos, U. Simsekli, R. M. Gower, "SGD with Clipping is Secretly Estimating the Median Gradient", arXiv, 2024
P. Viallard, M. Haddouche, U. Simsekli, B. Guedj, "Tighter Generalisation Bounds via Interpolation", arXiv, 2024
M. Haddouche, P. Viallard, U. Simsekli, B. Guedj, "A PAC-Bayesian Link Between Generalisation and Flat Minima", arXiv, 2024
Y. Wan, M. Barsbey, A. Zaidi, U. Simsekli, "Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD", arXiv, 2023
M. Gurbuzbalaban, Y. Hu, U. Simsekli, K. Yuan, L. Zhu, "Heavy-Tail Phenomenon in Decentralized SGD", arXiv, 2022
U. Şimşekli, M. Gürbüzbalaban, L. Sagun, T. H. Nguyen, G. Richard, "On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks", arXiv, 2019
Journals
M. Gürbüzbalaban, Y. Hu, U. Şimşekli, L. Zhu, "Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD", Transactions of Machine Learning Research (TMLR), 2023
A. Fallah, M. Gurbuzbalaban, A. Ozdaglar, U. Şimşekli, L. Zhu, "Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks", Journal of Machine Learning Research (JMLR), 2022
U. Şimşekli, O. Sener, G. Deligiannidis, M. A. Erdogdu, "Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks", Journal of Statistical Mechanics: Theory and Experiment (JSTAT), 2021 (Invited paper — Updated version of the NeurIPS 2020 paper)
S. Yildirim, M. B. Kurutmaz, M. Barsbey, U. Simsekli, A. T. Cemgil, "Bayesian Allocation Model: Marginal Likelihood-based Model Selection for Count Tensors", IEEE Journal of Selected Topics in Signal Processing (JSTSP), 2020
K. Kaya, F. Oztoprak, S. I. Birbil, A. T. Cemgil, U. Şimşekli, N. Kuru, H. Koptagel, M. K. Ozturk, “A framework for parallel second order incremental optimization algorithms for solving partially separable problems”, Computational Optimization and Applications (COAP), 2019
T. H. Nguyen, U. Şimşekli, G. Richard, A. T. Cemgil, "Efficient Bayesian Model Selection in PARAFAC via Stochastic Thermodynamic Integration", IEEE Signal Processing Letters (SPL), 2018
U. Şimşekli, A. Liutkus, A. T. Cemgil, “Alpha-Stable Matrix Factorization”, IEEE Signal Processing Letters (SPL), 2015 — Supplementary Doc.
International Conferences
K. Pavasovic, A. Durmus, U. Şimşekli, "Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent", Advances in Neural Information Processing Systems Conference (NeurIPS), New Orleans, LA, 2023 (Spotlight Presentation)
L. Zhu, M. Gurbuzbalaban, A. Raj, U. Şimşekli, "Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent", Advances in Neural Information Processing Systems Conference (NeurIPS), New Orleans, LA, 2023
P. Viallard, M. Haddouche, U. Şimşekli, B. Guedj, "Learning via Wasserstein-Based High Probability Generalisation Bounds", Advances in Neural Information Processing Systems Conference (NeurIPS), New Orleans, LA, 2023
A. Raj, U. Şimşekli, A. Rudi, "Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models", Advances in Neural Information Processing Systems Conference (NeurIPS), New Orleans, LA, 2023
S. Sachs, T. van Erven, L. Hodgkinson, R. Khanna, U. Şimşekli, "Generalization Guarantees via Algorithm-Dependent Rademacher Complexity", Conference on Learning Theory (COLT), Bangalore, India, 2023
B. Dupuis, G. Deligiannidis, U. Şimşekli, "Generalization Bounds with Data-dependent Fractal Dimensions", International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, 2023
A. Raj, L. Zhu, M. Gurbuzbalaban, U. Şimşekli, "Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions", International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, 2023
A. Raj, M. Barsbey, M. Gurbuzbalaban, L. Zhu, U. Simsekli, "Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares", International Conference on Algorithmic Learning Theory (ALT), Singapore, 2023
S. Park, U. Simsekli, M. A. Erdogdu, "Generalization Bounds for Stochastic Gradient Descent via Localized ε-Covers", Advances in Neural Information Processing Systems Conference (NeurIPS), New Orleans, LA, 2022
S. H. Lim, Y. Wan, U. Simsekli, "Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent", Advances in Neural Information Processing Systems Conference (NeurIPS), New Orleans, LA, 2022
M. Sefidgaran, A. Gohari, G. Richard, U. Simsekli, "Rate-distortion theoretic generalization bounds for stochastic learning algorithms", Conference on Learning Theory (COLT), London, UK, 2022
L. Hodgkinson, U. Simsekli, R. Khanna, M. W. Mahoney, "Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers", International Conference on Machine Learning (ICML), Baltimore, MD, USA, 2022
S. Kolouri, K. Nadjahi, S. Shahrampour, U. Şimşekli, "Generalized Sliced Probability Metrics", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Singapore, 2022 (Best Paper Award)
A. Camuto, G. Deligiannidis, M. A. Erdogdu, M. Gurbuzbalaban, U. Simsekli, L. Zhu, "Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms", Advances in Neural Information Processing Systems Conference (NeurIPS), 2021 (Spotlight Presentation)
M. Barsbey, M. Sefidgaran, M. A. Erdogdu, G. Richard, U. Simsekli, "Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks", Advances in Neural Information Processing Systems Conference (NeurIPS), 2021
K. Nadjahi, A. Durmus, P. E. Jacob, R. Badeau, U. Simsekli, "Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections", Advances in Neural Information Processing Systems Conference (NeurIPS), 2021
H. Wang, M. Gurbuzbalaban, L. Zhu, U. Simsekli, M. A. Erdogdu, "Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance", Advances in Neural Information Processing Systems Conference (NeurIPS), 2021
T. Birdal, A. Lou, L. Guibas, U. Simsekli, "Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks", Advances in Neural Information Processing Systems Conference (NeurIPS), 2021
M. Gurbuzbalaban, U. Simsekli, L. Zhu, "The Heavy-Tail Phenomenon in SGD", International Conference on Machine Learning (ICML), 2021
A. Camuto, X. Wang, L. Zhu, C. Holmes, M. Gurbuzbalaban, U. Simsekli, "Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections", International Conference on Machine Learning (ICML), 2021
A. Liutkus, O. Cifka, S-L. Wu, U. Simsekli, Y-H. Yang, G. Richard, "Relative Positional Encoding for Transformers with Linear Complexity", International Conference on Machine Learning (ICML), 2021 (Long Oral Presentation)
U. Şimşekli, O. Sener, G. Deligiannidis, M. A. Erdogdu, "Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks", Advances in Neural Information Processing Systems Conference (NeurIPS), 2020 (Spotlight Presentation)
K. Nadjahi, A. Durmus, L. Chizat, S. Kolouri, S. Shahrampour, U. Şimşekli, "Statistical and Topological Properties of Sliced Probability Divergences", Advances in Neural Information Processing Systems Conference (NeurIPS), 2020 (Spotlight Presentation)
V. De Bortoli, A. Durmus, X. Fontaine, U. Şimşekli, "Quantitative Propagation of Chaos for SGD in Wide Neural Networks", Advances in Neural Information Processing Systems Conference (NeurIPS), 2020
A. Camuto, M. Willetts, U. Şimşekli, S. Roberts, C. Holmes, "Explicit Regularisation in Gaussian Noise Injections", Advances in Neural Information Processing Systems Conference (NeurIPS), 2020
U. Şimşekli, L. Zhu, Y. W. Teh, M. Gürbüzbalaban, "Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise", International Conference on Machine Learning (ICML), 2020
T. Birdal, M. Arbel, U. Şimşekli, L. Guibas, "Synchronizing Probability Measures on Rotations via Optimal Transport", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020
K. Nadjahi, V. De Bortoli, A. Durmus, R. Badeau, U. Şimşekli, "Approximate Bayesian Computation with the Sliced-Wasserstein Distance", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2020 (Best Student Paper Award)
T. H, Nguyen, U. Şimşekli, M. Gürbüzbalaban, G. Richard, "First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise", Advances in Neural Information Processing Systems Conference (NeurIPS), Vancouver, British Columbia, Canada, 2019 — Supplementary Doc.
K. Nadjahi, A. Durmus, U. Şimşekli, R. Badeau, "Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance", Advances in Neural Information Processing Systems Conference (NeurIPS), Vancouver, British Columbia, Canada, 2019 (Spotlight Presentation) — Supplementary Doc.
S. Kolouri, K. Nadjahi, U. Şimşekli, R. Badeau, G. K. Rohde, "Generalized Sliced Wasserstein Distances", Advances in Neural Information Processing Systems Conference (NeurIPS), Vancouver, British Columbia, Canada, 2019 — Supplementary Doc.
U. Şimşekli, L. Sagun, M. Gürbüzbalaban, "A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks", International Conference on Machine Learning (ICML), Long Beach, CA, USA, 2019 (Best Paper Honorable Mention Award — Long Oral Presentation)
A. Liutkus, U. Şimşekli, S. Majeswsky, A. Durmus, F. Stöter, “Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions”, International Conference on Machine Learning (ICML), Long Beach, CA, USA, 2019 (Long Oral Presentation)
T. H. Nguyen, U. Şimşekli, G. Richard, "Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization", International Conference on Machine Learning (ICML), Long Beach, CA, USA, 2019 — Supplementary Material
T. Birdal, U. Şimşekli, "Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019 (Oral Presentation, Best Paper Finalist)
T. Birdal, U. Şimşekli, M. O. Eken, S. Ilic, “Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC”, Advances in Neural Information Processing Systems Conference (NeurIPS), Montréal, Quebec, Canada, 2018 — Supplementary Material
U. Şimşekli, Ç. Yildiz, T. H. Nguyen, G. Richard, A. T. Cemgil, “Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization”, International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018
M. Jas, T. Dupré La Tour, U. Şimşekli, A. Gramfort, “Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding”, Advances in Neural Information Processing Systems (NIPS), Long Beach, CA, USA, 2017 — Supplementary Material
U. Şimşekli, “Fractional Langevin Monte Carlo: Exploring Lévy Driven Stochastic Differential Equations for MCMC”, International Conference on Machine Learning (ICML), Sydney, NSW, Australia, 2017 — Supplementary Doc.
U. Şimşekli, A. Durmus, R. Badeau, G. Richard, E. Moulines, A. T. Cemgil, "Parallelized Stochastic Gradient Markov Chain Monte Carlo Algorithms For Non-negative Matrix Factorization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), New Orleans, LA, USA, 2017
A. Durmus, U. Şimşekli, E. Moulines, R. Badeau, G. Richard, “Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo”, Advances in Neural Information Processing Systems (NIPS), Barcelona, Spain, 2016
U. Şimşekli, R. Badeau, A. T. Cemgil, G. Richard, “Stochastic Quasi-Newton Langevin Monte Carlo”, International Conference on Machine Learning (ICML), New York, NY, USA, 2016 — Supplementary Doc.
U. Şimşekli, R. Badeau, G. Richard, A. T. Cemgil, “Stochastic Thermodynamic Integration: Efficient Bayesian Model Selection via Stochastic Gradient MCMC”, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Shanghai, China, 2016 — Supplementary Doc.
U. Şimşekli, A. T. Cemgil, B. Ermis, “Learning Mixed Divergences in Coupled Matrix and Tensor Factorization Models”, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane, Australia, 2015 — Supplementary Doc.
U. Şimşekli, A. T. Cemgil, Y. K. Yilmaz, “Learning the Beta-Divergence in Tweedie Compound Poisson Matrix Factorization Models”, 30th International Conference on Machine Learning (ICML), Atlanta, Georgia, USA, 2013
U. Şimşekli, B. Ermis, A. T. Cemgil, E. Acar, “Optimal Weight Learning For Coupled Tensor Factorization With Mixed Divergences”, 21st European Signal Processing Conference (EUSIPCO), Marrakech, Morocco, 2013 (Invited paper) — Supplementary Doc.
U. Şimşekli, A. T. Cemgil, “Markov Chain Monte Carlo Inference For Probabilistic Latent Tensor Factorization”, IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Santander, Spain, 2012
Y. K. Yilmaz, A. T. Cemgil, U. Şimşekli, “Generalised Coupled Tensor Factorisation”, Advances in Neural Information Processing Systems (NIPS), Granada, Spain, 2011
International Workshops
F. Schaipp, U. Şimşekli, R. Gower, "Robust gradient estimation in the presence of heavy-tailed noise", Heavy Tails in Machine Learning Workshop (HT-ML), in Neural Information Processing Systems Conference (NeurIPS), New Orleans, Louisiana, USA, 2023
Y. Wan, A. Zaidi, U. Şimşekli, "Neural network compression with heavy-tailed SGD", Heavy Tails in Machine Learning Workshop (HT-ML), in Neural Information Processing Systems Conference (NeurIPS), New Orleans, Louisiana, USA, 2023
M. B. Kurutmaz, M. Barsbey, A. T. Cemgil, S. Yildirim, U. Şimşekli, "Bayesian Model Selection for Identifying Markov Equivalent Causal Graphs", Advances in Approximate Bayesian Inference Workshop (AABI), Vancouver, British Columbia, Canada, 2019
M. B. Kurutmaz, A. T. Cemgil, M. Barsbey, U. Şimşekli, S. Yildirim, "Bayesian Learning of Non-Negative Matrix/Tensor Factorizations by Simulating Polya Urns", Advances in Approximate Bayesian Inference Workshop (AABI), Montréal, Quebec, Canada, 2018
M. B. Kurutmaz, A. T. Cemgil, U. Şimşekli, S. Yildirim, "Bayesian Nonnegative Matrix Factorization as an Allocation Model", Advances in Approximate Bayesian Inference Workshop (AABI), in Neural Information Processing Systems Conference (NIPS), Long Beach, California, USA, 2017
U. Şimşekli, H. Koptagel, F. Oztoprak, S. I. Birbil, A. T. Cemgil, “HAMSI: Distributed Incremental Optimization Algorithm Using Quadratic Approximations for Partially Separable Problems”, Optimization for Machine Learning Workshop (OPT2015), in Neural Information Processing Systems Conference (NIPS), Montréal, Quebec, Canada, 2015
U. Şimşekli, B. Ermis, F. Oztoprak, S. Ilker Birbil, A. T. Cemgil, “Parallel and Distributed Inference in Coupled Tensor Factorization Models”, Workshop on Distributed Machine Learning and Matrix Computations, in Neural Information Processing Systems Conference (NIPS), Montréal, Quebec, Canada, 2014 — Supplementary Doc.
Technical Reports
A. T. Cemgil, M. B. Kurutmaz, S. Yildirim, M. Barsbey, U. Şimşekli, "Bayesian Allocation Model: Inference by Sequential Monte Carlo for Nonnegative Tensor Factorizations and Topic Models using Polya Urns", arXiv, 2019
U. Şimşekli, H. Koptagel, H. Guldas, A. T. Cemgil, F. Oztoprak, S. I. Birbil, “Parallel Stochastic Gradient Markov Chain Monte Carlo for Matrix Factorisation Models”, arXiv, 2015
Publications on Machine Learning Applications
Journals
O. Cífka, U. Şimşekli, G. Richard, "Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic Data", IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 2020
S. Henriet, U. Şimşekli, S. Dos Santos, B. Fuentes, G. Richard, "Independent-Variation Matrix Factorization with Application to Energy Disaggregation", IEEE Signal Processing Letters (SPL), 2019
S. Henriet, U. Şimşekli, G. Richard, B. Fuentes, "A Generative Model for Non-Intrusive Load Monitoring in Commercial Buildings", Energy and Buildings, Elsevier, 2018
U. Şimşekli, T. Virtanen, A. T. Cemgil, “Non-negative Tensor Factorization Models for Bayesian Audio Processing”, Digital Signal Processing (DSP), 2015
I. Ari, U. Şimşekli, A. T. Cemgil, L. Akarun “Randomized Matrix Decompositions and Exemplar Selection in Large Dictionaries for Polyphonic Piano Transcription”, Journal of New Music Research (JNMR), 2014
U. Şimşekli, B. Kurt, O. Sonmez, A. T. Cemgil, “Combined Perception and Control for Robotic Performance”, EURASIP Journal on Audio, Speech, and Music Processing (JASMP), 2012
U. Şimşekli, A. T. Cemgil, “Probabilistic Models for Real-Time Acoustic Event Detection with Application to Pitch Tracking”, Journal of New Music Research (JNMR), 2011
U. Şimşekli, A. Jylhä, C. Erkut, A. T. Cemgil, “Real-Time Recognition of Percussive Sounds by a Model-Based Method”, EURASIP Journal on Advances in Signal Processing (JASP), 2011
International Conferences
O. Cífka, A. Ozerov, U. Şimşekli, G. Richard, "Self-Supervised VQ-VAE For One-Shot Music Style Transfer", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021
O. Cífka, U. Şimşekli, G. Richard, "Supervised Symbolic Music Style Translation Using Synthetic Data", Conference of the International Society for Music Information Retrieval (ISMIR), Delft, The Netherlands, 2019
S. Leglaive, U. Şimşekli, A. Liutkus, L. Girin, R. Horaud, "Speech Enhancement with Variational Autoencoders and Alpha-Stable Distributions", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brighton, UK, 2019
M. Fontaine, F. R. Stöter, A. Liutkus, U. Şimşekli, R. Serizel, R. Badeau, "Multichannel Audio Modeling with Elliptically Stable Tensor Decomposition", International Conference on Latent Variable Analysis and Signal Separation (LVA-ICA), Guildford, UK, 2018
U. Şimşekli, H. Erdoğan, S. Leglaive, A. Liutkus, R. Badeau, G. Richard, "Alpha-stable Low-rank Plus Residual Decomposition For Speech Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Calgary, AB, Canada, 2018
S. Leglaive, U. Şimşekli, A. Liutkus, R. Badeau, G. Richard, "Alpha-stable Multichannel Audio Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), New Orleans, LA, USA, 2017 — Supplementary Document
A. Liutkus, U. Şimşekli, A. T. Cemgil, “Extraction of Temporal Patterns in Multi-rate and Multi-modal Datasets”, International Conference on Latent Variable Analysis and Signal Separation (LVA-ICA), Liberec, Czech Republic, 2015
U. Şimşekli, T. Birdal, “A Unified Probabilistic Framework For Robust Decoding Of Linear Barcodes”, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane, Australia, 2015
A. Holzapfel, U. Şimşekli, A. T. Cemgil, “Section-Level Modeling Of Musical Audio For Linking Performances To Scores In Turkish Makam Music”, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane, Australia, 2015
U. Şimşekli, J. Le Roux, J. R. Hershey “Non-negative Source-Filter Dynamical System for Speech Enhancement”, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Florence, Italy, 2014
U. Şimşekli, J. Le Roux, J. R. Hershey “Hierarchical and Coupled Non-negative Dynamical Systems with Application to Audio Modeling”, IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA, 2013
U. Şimşekli, Y. K. Yilmaz, A. T. Cemgil, “Score Guided Audio Restoration via Generalised Coupled Tensor Factorisation”, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto, Japan, 2012 (Invited paper)
U. Şimşekli, A. T. Cemgil, “Score Guided Musical Source Separation Using Generalized Coupled Tensor Factorization”, 20th European Signal Processing Conference (EUSIPCO), Bucharest, Romania, 2012 (Invited paper)
İ. Arı, U. Şimşekli, A. T. Cemgil, L. Akarun, “Large Scale Polyphonic Music Transcription Using Randomized Matrix Decompositions”, 20th European Signal Processing Conference (EUSIPCO), Bucharest, Romania, 2012
A. Jylhä, C. Erkut, U. Şimşekli, A. T. Cemgil “Sonic Handprints: Person Identification with Hand Clapping Sounds by a Model-Based Method”, AES 45th International Conference (AES), Helsinki, Finland, 2012
A. T. Cemgil, U. Şimşekli, Y. C. Sübakan, “Probabilistic Tensor Factorization Framework for Audio Modeling”, IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA, 2011
U. Şimşekli, “Automatic Music Genre Classification Using Bass Lines”, 20th IAPR International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, 2010
U. Şimşekli, A. T. Cemgil, “A Comparison of Probabilistic Models for Online Pitch Tracking”, 7th Sound and Music Computing Conference (SMC), Barcelona, Spain, 2010
International Workshops
S. Henriet, U. Şimşekli, G. Richard, B. Fuentes, "Matrix Factorization for High Frequency Non Intrusive Load Monitoring: Definitions and Algorithms", International Workshop on Non-Intrusive Load Monitoring (NILM) @ ACM BuildSys, (2020)
S. Henriet, U. Şimşekli, G. Richard, B. Fuentes, "Energy Disaggregation for Commercial Buildings: A Statistical Analysis", 4th International Workshop on Non-Intrusive Load Monitoring (NILM), Austin, TX, USA, 2018
S. Henriet, U. Şimşekli, G. Richard, B. Fuentes, "Poster: Synthetic Dataset Generation for Non-Intrusive Load Monitoring in Commercial Buildings", ACM BuildSys, Delft, The Netherlands, 2017
U. Şimşekli, H. Koptagel, A. T. Cemgil, F. Oztoprak, S. I. Birbil, “Scalable Distributed Tensor Factorizations with Incremental Quadratic Approximations”, Workshop on Tensor Decompositions and Applications (TDA), Leuven, Belgium, 2016
U. Şimşekli, Y. E. Kara, A. Ozgur, A. T. Cemgil, “Probabilistic Latent Tensor Factorization for 3-way Microarray Data Analysis with Missing Values”, Machine Learning in Computational Biology Workshop (MLCB) in Neural Information Processing Systems Conference (NIPS), Lake Tahoe, Nevada, USA, 2012
National Conferences (in Turkish or French)
S. Henriet, U. Şimşekli, S. Dos Santos, B. Fuentes, G. Richard, "Factorisation Matricielle Semi Non-Négative: Application à la Décomposition de Consommations Electriques", Proc. of the XXVIIe Colloque GRETSI, Lille, France, 2019
U. Şimşekli, T. Birdal, E. Koc, A. T. Cemgil, “Çevrimiçi Servisler için Ayrışım Tabanlı Tavsiye Sistemi”, “A Factorization Based Recommender System for Online Services”, 21st IEEE Conference on Signal Processing and Communications Applications (SİU), Muğla, Turkey, 2013 (Alper Atalay best student paper award)
U. Şimşekli, Y. K. Yılmaz, A. T. Cemgil, “Çoksesli Müzik Notalandırması İçin Bağlaşımlı Tensör Ayrışım Modelleri”, “Coupled Tensor Factorization Models for Polyphonic Music Transcription”, 20th IEEE Conference on Signal Processing and Communications Applications (SİU), Muğla, Turkey, 2012
İ. Arı, U. Şimşekli, A. T. Cemgil, L. Akarun, “TDA-Tabanlı Çoksesli Müzik Notalandırma”, “SVD-based Polyphonic Music Transcription”, 20th IEEE Conference on Signal Processing and Communications Applications (SİU), Fethiye, Turkey, 2012 (Nominated for best student paper award)
U. Şimşekli, Y. C. Subakan, A. T. Cemgil, "Negatif Olmayan Modeller İçin Saklı Tensör Ayrışımı Çerçevesi", "A Latent Tensor Factorization Framework for Non-Negative Convolutive Models", 19th IEEE Conference on Signal Processing and Communications Applications (SİU), Antalya, Turkey, 2011