Filtrer vos résultats
- 32
- 30
- 51
- 8
- 3
- 29
- 23
- 14
- 2
- 1
- 2
- 10
- 6
- 10
- 8
- 10
- 7
- 4
- 3
- 2
- 61
- 1
- 39
- 26
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 62
- 21
- 12
- 10
- 8
- 7
- 7
- 6
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
62 résultats
|
Approximate Bayesian computation with the sliced-Wasserstein distance45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain. ⟨10.1109/icassp40776.2020.9054735⟩
Communication dans un congrès
hal-02457063v1
|
||
|
Parallelized Stochastic Gradient Markov Chain Monte Carlo Algorithms for Non-Negative Matrix Factorization42nd International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Mar 2017, New Orleans, United States
Communication dans un congrès
hal-01416357v1
|
||
|
Generalized Sliced Wasserstein DistancesNeurIPS 2019, Dec 2019, Vancouver, Canada
Communication dans un congrès
hal-02280948v1
|
||
|
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural NetworksInternational Conference on Machine Learning, Jun 2019, Long Beach, United States
Communication dans un congrès
hal-03269101v1
|
||
|
Generalization Bounds using Data-Dependent Fractal DimensionsInternational Conference on Machine Learning (ICML 2023), Jul 2023, Honolulu, United States
Communication dans un congrès
hal-04438550v1
|
||
Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein DistanceNeurIPS 2019, Dec 2019, Vancouver, Canada
Communication dans un congrès
hal-02280944v1
|
|||
|
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Dec 2019, Vancouver, Canada
Communication dans un congrès
hal-02372376v1
|
||
|
Supervised Symbolic Music Style Translation Using Synthetic Data20th International Society for Music Information Retrieval Conference (ISMIR), Nov 2019, Delft, Netherlands. ⟨10.5281/zenodo.3527878⟩
Communication dans un congrès
hal-02366954v1
|
||
|
Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning AlgorithmsCOLT 2022 - 35th Annual Conference on Learning Theory, Jul 2022, London, United Kingdom
Communication dans un congrès
hal-03759597v1
|
||
|
Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections35th Conference on Neural Information Processing Systems (NeurIPS 2021), Dec 2021, En ligne, France
Communication dans un congrès
hal-03494781v1
|
||
|
Alpha-Stable Multichannel Audio Source Separation42nd International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Mar 2017, New Orleans, United States
Communication dans un congrès
hal-01416366v1
|
||
|
Stochastic thermodynamic integration: efficient Bayesian model selection via stochastic gradient MCMC41st International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, Shanghai, China
Communication dans un congrès
hal-01248011v1
|
||
|
Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic DataIEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, 28, pp.2638-2650. ⟨10.1109/TASLP.2020.3019642⟩
Article dans une revue
hal-02923548v2
|
||
|
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient NoiseInternational Conference on Machine Learning, 2020, Online, France
Communication dans un congrès
hal-03269112v1
|
||
|
Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks35th Conference on Neural Information Processing Systems (NeurIPS), Dec 2021, Online, United States
Communication dans un congrès
hal-03413484v1
|
||
|
Stochastic Gradient Richardson-Romberg Markov Chain Monte CarloThirtieth Annual Conference on Neural Information Processing Systems (NIPS), Dec 2016, Barcelone, Spain
Communication dans un congrès
hal-01354064v1
|
||
|
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise InjectionsICML 2021 - Thirty-eighth annual conference International Conference on Machine Learning, Jul 2021, Virtual, France
Communication dans un congrès
hal-03530315v1
|
||
|
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient DescentNeurIPS 2022 - Thirty-sixth Conference on Neural Information Processing Systems, Nov 2022, New Orleans, United States
Communication dans un congrès
hal-03935819v1
|
||
|
Tighter Generalisation Bounds via Interpolation2024
Pré-publication, Document de travail
hal-04456925v1
|
||
|
Explicit Regularisation in Gaussian Noise InjectionsAdvances in Neural Processing Systems, 2020, Online, France
Communication dans un congrès
hal-03269116v1
|
||
|
Generalization Bounds using Lower Tail Exponents in Stochastic OptimizersICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore, United States
Communication dans un congrès
hal-03935798v1
|
||
|
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent NetworksJournal of Machine Learning Research, 2022
Article dans une revue
hal-03857867v1
|
||
|
Stochastic Quasi-Newton Langevin Monte CarloInternational Conference on Machine Learning (ICML), Jun 2016, New York, NY, United States
Communication dans un congrès
hal-01306596v1
|
||
Energy Disaggregation for Commercial Buildings: A Statistical Analysis», International Workshop on Non-Intrusive Load Monitoring (NILM2018), Mar 2018, Austin, Tx, United States
Communication dans un congrès
hal-02288000v1
|
|||
|
Efficient Bayesian Model Selection in PARAFAC via Stochastic Thermodynamic IntegrationIEEE Signal Processing Letters, 2018
Article dans une revue
hal-01779074v1
|
||
|
Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse CodingAdvances in neural information processing systems, Dec 2017, Long Beach, United States
Communication dans un congrès
hal-01590988v1
|
||
|
Intrinsic Dimension, Persistent Homology and Generalization in Neural NetworksNeurIPS 2021 - Thirty-fifth Conference on Neural Information Processing Systems, Dec 2021, Virtual, France
Communication dans un congrès
hal-03530322v1
|
||
The Heavy-Tail Phenomenon in SGDICML2021 - Thirty-eighth annual conference on International Conference on Machine Learning, Jul 2021, Virtual, France
Communication dans un congrès
hal-03530319v1
|
|||
|
Multichannel Audio Modeling with Elliptically Stable Tensor DecompositionLVA/ICA 2018 - 14th International Conference on Latent Variable Analysis and Signal Separation, Jul 2018, Surrey, United Kingdom. pp.13-23, ⟨10.1007/978-3-319-93764-9_2⟩
Communication dans un congrès
lirmm-01766795v1
|
||
|
Factorisation Matricielle Semi Non-Négative: Applicationà la Décomposition de Consommations ElectriquesColloque francophonede traitement du signal et des images (GRETSI), Aug 2019, Lille, France
Communication dans un congrès
hal-02381367v1
|