A non-parametric rehearsal learning framework using conditional mean embeddings and a Probit surrogate for avoiding undesired outcomes, with consistency guarantees.
arXiv preprint arXiv:1907.02392 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
In this work, we address the task of natural image generation guided by a conditioning input. We introduce a new architecture called conditional invertible neural network (cINN). The cINN combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preprocesses the conditioning input into useful features. All parameters of the cINN are jointly optimized with a stable, maximum likelihood-based training procedure. By construction, the cINN does not experience mode collapse and generates diverse samples, in contrast to e.g. cGANs. At the same time our model produces sharp images since no reconstruction loss is required, in contrast to e.g. VAEs. We demonstrate these properties for the tasks of MNIST digit generation and image colorization. Furthermore, we take advantage of our bi-directional cINN architecture to explore and manipulate emergent properties of the latent space, such as changing the image style in an intuitive way.
representative citing papers
Order-based rehearsal learning learns sufficient order structures from observational data to make decisions avoiding undesired events, outperforming graph-based methods and matching oracle graph baselines in experiments.
Two new diffusion-based models (HCDM and BDDM) are developed and validated for bounded continuous response and reaction-time data using amortized Bayesian methods.
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
A flow-matching generative model trained on CoLBT-hydro data conditionally generates marginal final-state hadron spectra from jet-induced hydro responses in 0-10% Pb+Pb collisions at 5.02 TeV, matching training data statistics with approximately six orders of magnitude computational speedup.
Invertible Neural Networks are used to generate gas turbine combustor designs that meet specified performance criteria from a training database of parameterized designs and simulations.
citing papers explorer
-
Non-Parametric Rehearsal Learning via Conditional Mean Embeddings
A non-parametric rehearsal learning framework using conditional mean embeddings and a Probit surrogate for avoiding undesired outcomes, with consistency guarantees.
-
Order-based Rehearsal Learning
Order-based rehearsal learning learns sufficient order structures from observational data to make decisions avoiding undesired events, outperforming graph-based methods and matching oracle graph baselines in experiments.
-
Extending Evidence Accumulation Models to Bounded Continuous Self-report Data
Two new diffusion-based models (HCDM and BDDM) are developed and validated for bounded continuous response and reaction-time data using amortized Bayesian methods.
-
Diffusion Posterior Sampling for General Noisy Inverse Problems
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
-
A flow-matching generative model for event-by-event jet-induced hydro response in high-energy heavy-ion collisions
A flow-matching generative model trained on CoLBT-hydro data conditionally generates marginal final-state hadron spectra from jet-induced hydro responses in 0-10% Pb+Pb collisions at 5.02 TeV, matching training data statistics with approximately six orders of magnitude computational speedup.
-
Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks
Invertible Neural Networks are used to generate gas turbine combustor designs that meet specified performance criteria from a training database of parameterized designs and simulations.