Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Durkan, Conor"'
Autor:
Du, Yilun, Durkan, Conor, Strudel, Robin, Tenenbaum, Joshua B., Dieleman, Sander, Fergus, Rob, Sohl-Dickstein, Jascha, Doucet, Arnaud, Grathwohl, Will
Since their introduction, diffusion models have quickly become the prevailing approach to generative modeling in many domains. They can be interpreted as learning the gradients of a time-varying sequence of log-probability density functions. This int
Externí odkaz:
http://arxiv.org/abs/2302.11552
Autor:
Dieleman, Sander, Sartran, Laurent, Roshannai, Arman, Savinov, Nikolay, Ganin, Yaroslav, Richemond, Pierre H., Doucet, Arnaud, Strudel, Robin, Dyer, Chris, Durkan, Conor, Hawthorne, Curtis, Leblond, Rémi, Grathwohl, Will, Adler, Jonas
Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges on the fact that the underlying physical phenomena are continuous. Fo
Externí odkaz:
http://arxiv.org/abs/2211.15089
Score-based diffusion models synthesize samples by reversing a stochastic process that diffuses data to noise, and are trained by minimizing a weighted combination of score matching losses. The log-likelihood of score-based diffusion models can be tr
Externí odkaz:
http://arxiv.org/abs/2101.09258
Autor:
Tejero-Cantero, Alvaro, Boelts, Jan, Deistler, Michael, Lueckmann, Jan-Matthis, Durkan, Conor, Gonçalves, Pedro J., Greenberg, David S., Macke, Jakob H.
Scientists and engineers employ stochastic numerical simulators to model empirically observed phenomena. In contrast to purely statistical models, simulators express scientific principles that provide powerful inductive biases, improve generalization
Externí odkaz:
http://arxiv.org/abs/2007.09114
Likelihood-free methods perform parameter inference in stochastic simulator models where evaluating the likelihood is intractable but sampling synthetic data is possible. One class of methods for this likelihood-free problem uses a classifier to dist
Externí odkaz:
http://arxiv.org/abs/2002.03712
A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the parameteri
Externí odkaz:
http://arxiv.org/abs/1906.04032
A normalizing flow models a complex probability density as an invertible transformation of a simple density. The invertibility means that we can evaluate densities and generate samples from a flow. In practice, autoregressive flow-based models are sl
Externí odkaz:
http://arxiv.org/abs/1906.02145
Autor:
Nash, Charlie, Durkan, Conor
Neural density estimators are flexible families of parametric models which have seen widespread use in unsupervised machine learning in recent years. Maximum-likelihood training typically dictates that these models be constrained to specify an explic
Externí odkaz:
http://arxiv.org/abs/1904.05626
Likelihood-free inference refers to inference when a likelihood function cannot be explicitly evaluated, which is often the case for models based on simulators. Most of the literature is based on sample-based `Approximate Bayesian Computation' method
Externí odkaz:
http://arxiv.org/abs/1811.08723
Autor:
Durkan, Conor
Given a dataset of examples, distribution estimation is the task of approximating the assumed underlying probability distribution from which those samples were drawn. Neural distribution estimation relies on the powerful function approximation capabi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______463::9746a9925cfe14263132128866ef6ebb
https://hdl.handle.net/1842/39846
https://hdl.handle.net/1842/39846