Recherche - Archive ouverte HAL

62 résultats

	Pour les 62 documents Envoyer sur ORCID RSS ATOM Exporter BibTeX XML-TEI CSV RTF EndNote PDF HTML Export avancé	Page : Page précédente 1 2 3 Page suivante	triés par Pertinence Auteur A→Z Auteur Z→A Titre A→Z Titre Z→A Date de publication croissante Date de publication décroissante Date de dépôt croissante Date de dépôt décroissante

		Approximate Bayesian computation with the sliced-Wasserstein distance Kimia Nadjahi , Valentin de Bortoli , Alain Durmus , Roland Badeau , Umut Şimşekli 45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain. ⟨10.1109/icassp40776.2020.9054735⟩ Communication dans un congrès hal-02457063v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Parallelized Stochastic Gradient Markov Chain Monte Carlo Algorithms for Non-Negative Matrix Factorization Umut Şimşekli , Alain Durmus , Roland Badeau , Gael Richard , Éric Moulines , et al. 42nd International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Mar 2017, New Orleans, United States Communication dans un congrès hal-01416357v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Generalized Sliced Wasserstein Distances Soheil Kolouri , Kimia Nadjahi , Umut Şimşekli , Roland Badeau , Gustavo K. Rohde NeurIPS 2019, Dec 2019, Vancouver, Canada Communication dans un congrès hal-02280948v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks Umut Şimşekli , Levent Sagun , Mert Gurbuzbalaban International Conference on Machine Learning, Jun 2019, Long Beach, United States Communication dans un congrès hal-03269101v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections Kimia Nadjahi , Alain Durmus , Pierre E. Jacob , Roland Badeau , Umut Şimşekli 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Dec 2021, En ligne, France Communication dans un congrès hal-03494781v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Supervised Symbolic Music Style Translation Using Synthetic Data Ondřej Cífka , Umut Şimşekli , Gael Richard 20th International Society for Music Information Retrieval Conference (ISMIR), Nov 2019, Delft, Netherlands. ⟨10.5281/zenodo.3527878⟩ Communication dans un congrès hal-02366954v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms Milad Sefidgaran , Amin Gohari , Gael Richard , Umut Şimşekli COLT 2022 - 35th Annual Conference on Learning Theory, Jul 2022, London, United Kingdom Communication dans un congrès hal-03759597v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise Thanh Huy Nguyen , Umut Şimşekli , Mert Gürbüzbalaban , Gael Richard 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Dec 2019, Vancouver, Canada Communication dans un congrès hal-02372376v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Generalization Bounds using Data-Dependent Fractal Dimensions Benjamin Dupuis , George Deligiannidis , Umut Şimşekli International Conference on Machine Learning (ICML 2023), Jul 2023, Honolulu, United States Communication dans un congrès hal-04438550v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Alpha-Stable Multichannel Audio Source Separation Simon Leglaive , Umut Şimşekli , Antoine Liutkus , Roland Badeau , Gael Richard 42nd International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Mar 2017, New Orleans, United States Communication dans un congrès hal-01416366v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance Kimia Nadjahi , Alain Durmus , Umut Şimşekli , Roland Badeau NeurIPS 2019, Dec 2019, Vancouver, Canada Communication dans un congrès hal-02280944v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Explicit Regularisation in Gaussian Noise Injections Alexander Camuto , Matthew Willetts , Umut Şimşekli , Stephen Roberts , Chris Holmes Advances in Neural Processing Systems, 2020, Online, France Communication dans un congrès hal-03269116v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers Liam Hodgkinson , Umut Şimşekli , Rajiv Khanna , Michael W. Mahoney ICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore, United States Communication dans un congrès hal-03935798v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks Alireza Fallah , Mert Gurbuzbalaban , Asuman Ozdaglar , Umut Şimşekli , Lingjiong Zhu Journal of Machine Learning Research, 2022 Article dans une revue hal-03857867v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Stochastic Quasi-Newton Langevin Monte Carlo Umut Şimşekli , Roland Badeau , Taylan Cemgil , Gael Richard International Conference on Machine Learning (ICML), Jun 2016, New York, NY, United States Communication dans un congrès hal-01306596v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Energy Disaggregation for Commercial Buildings: A Statistical Analysis Simon Henriet , Umut Şimşekli , Gael Richard , Benoît Fuentes », International Workshop on Non-Intrusive Load Monitoring (NILM2018), Mar 2018, Austin, Tx, United States Communication dans un congrès hal-02288000v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Efficient Bayesian Model Selection in PARAFAC via Stochastic Thermodynamic Integration Thanh Huy Nguyen , Umut Şimşekli , Gael Richard , Ali Taylan Cemgil IEEE Signal Processing Letters, 2018 Article dans une revue hal-01779074v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding Mainak Jas , Tom Dupré La Tour , Umut Şimşekli , Alexandre Gramfort Advances in neural information processing systems, Dec 2017, Long Beach, United States Communication dans un congrès hal-01590988v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Stochastic thermodynamic integration: efficient Bayesian model selection via stochastic gradient MCMC Umut Şimşekli , Roland Badeau , Gael Richard , Ali Taylan Cemgil 41st International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, Shanghai, China Communication dans un congrès hal-01248011v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic Data Ondřej Cífka , Umut Şimşekli , Gael Richard IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, 28, pp.2638-2650. ⟨10.1109/TASLP.2020.3019642⟩ Article dans une revue hal-02923548v2	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise Umut Şimşekli , Lingjiong Zhu , Yee Whye Teh , Mert Gürbüzbalaban International Conference on Machine Learning, 2020, Online, France Communication dans un congrès hal-03269112v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks Melih Barsbey , Milad Sefidgaran , Murat A Erdogdu , Gael Richard , Umut Şimşekli 35th Conference on Neural Information Processing Systems (NeurIPS), Dec 2021, Online, United States Communication dans un congrès hal-03413484v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo Alain Durmus , Umut Şimşekli , Éric Moulines , Roland Badeau , Gael Richard Thirtieth Annual Conference on Neural Information Processing Systems (NIPS), Dec 2016, Barcelone, Spain Communication dans un congrès hal-01354064v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections Alexander Camuto , Xiaoyu Wang , Lingjiong Zhu , Chris Holmes , Mert Gürbüzbalaban , et al. ICML 2021 - Thirty-eighth annual conference International Conference on Machine Learning, Jul 2021, Virtual, France Communication dans un congrès hal-03530315v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent Soon Hoe Lim , Yijun Wan , Umut Şimşekli NeurIPS 2022 - Thirty-sixth Conference on Neural Information Processing Systems, Nov 2022, New Orleans, United States Communication dans un congrès hal-03935819v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Tighter Generalisation Bounds via Interpolation Paul Viallard , Maxime Haddouche , Umut Şimşekli , Benjamin Guedj 2024 Pré-publication, Document de travail hal-04456925v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares Anant Raj , Melih Barsbey , Mert Gürbüzbalaban , Lingjiong Zhu , Umut Şimşekli ALT 2023 - 34th International Conference on Algorithmic Learning Theory, Feb 2023, Singapore, Singapore Communication dans un congrès hal-04478947v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize Mert Gürbüzbalaban , Yuanhan Hu , Umut Şimşekli , Lingjiong Zhu Transactions on Machine Learning Research Journal, 2023 Article dans une revue hal-04478948v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Relative Positional Encoding for Transformers with Linear Complexity Antoine Liutkus , Ondřej Cífka , Shih-Lun Wu , Umut Şimşekli , Yi-Hsuan Yang , et al. ICML 2021 - 38th International Conference on Machine Learning, Jul 2021, Virtual Only, United States. pp.7067-7079 Communication dans un congrès hal-03256451v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More
		Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions Anant Raj , Lingjiong Zhu , Mert Gürbüzbalaban , Umut Şimşekli ICML 2023 - International Conference on Machine Learning, Jul 2023, Honolulu, United States Communication dans un congrès hal-04478946v1	Envoyer sur ORCID Exporter BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite Export avancé Partager Gmail Facebook X LinkedIn More

Filtrer vos résultats

Approximate Bayesian computation with the sliced-Wasserstein distance

Parallelized Stochastic Gradient Markov Chain Monte Carlo Algorithms for Non-Negative Matrix Factorization

Generalized Sliced Wasserstein Distances

A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks

Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections

Supervised Symbolic Music Style Translation Using Synthetic Data

Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms

First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise

Generalization Bounds using Data-Dependent Fractal Dimensions

Alpha-Stable Multichannel Audio Source Separation

Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance

Explicit Regularisation in Gaussian Noise Injections

Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers

Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks

Stochastic Quasi-Newton Langevin Monte Carlo

Energy Disaggregation for Commercial Buildings: A Statistical Analysis

Efficient Bayesian Model Selection in PARAFAC via Stochastic Thermodynamic Integration

Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding

Stochastic thermodynamic integration: efficient Bayesian model selection via stochastic gradient MCMC

Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic Data

Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise

Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks

Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo

Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections

Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent

Tighter Generalisation Bounds via Interpolation

Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares

Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize

Relative Positional Encoding for Transformers with Linear Complexity

Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions