Search Results for author:
Found 4 papers, 2 papers with code
Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint
Solving image inverse problems (e. g., super-resolution and inpainting) requires generating a high fidelity image that matches the given input (the low-resolution image or the masked image).
On the Generative Utility of Cyclic Conditionals
This is motivated by the observation that deep generative models, in addition to a likelihood model $p(x|z)$, often also use an inference model $q(z|x)$ for extracting representation, but they rely on a usually uninformative prior distribution $p(z)$ to define a joint distribution, which may render problems like posterior collapse and manifold mismatch.
Learning Causal Semantic Representation for Out-of-Distribution Prediction
Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.
Cache Updating Strategy Minimizing the Age of Information with Time-Varying Files' Popularities
Inspired by this solution for the relaxed problem, we propose a practical cache updating strategy that meets all the constraints of the original problem.
Information Theory Information Theory
