We propose a first-order sampling method called the Metropolis-adjusted Preconditioned Langevin Algorithm for approximate sampling from a target distribution whose support is a proper convex subset of Rd. Our proposed...
详细信息
We propose a new method called the Metropolis-adjusted Mirror Langevin algorithm for approximate sampling from distributions whose support is a compact and convex set. This algorithm adds an accept-reject filter to th...
详细信息
Silicon field emitter arrays (FEAs) -based cold cathodes have shown promise in many applications under harsh environments such as x-ray sources and high-power microwave devices due to the temperature independence of t...
详细信息
This paper investigates the optimized combination of rotor and stator teeth in a three-phase switched reluctance motor featuring a connected C-core topology to attain a larger winding area and, thus, a higher electric...
详细信息
A new three-phase hybrid-excited multi-tooth switched reluctance motor with embedded permanent magnets is proposed, capable of achieving higher torque density for transportation electrification applications. Operating...
详细信息
The discovery of CRISPR-mediated gene activation (CRISPRa) has transformed the way in which we perform genetic screening, bioproduction and therapeutics through its ability to scale and multiplex. However, the emergen...
详细信息
Shape-based virtual screening is widely used in ligand-based drug design to search chemical libraries for molecules with similar 3D shapes yet novel 2D graph structures compared to known ligands. 3D deep generative mo...
详细信息
There have been several developments in renewable resources, standby sources of energy, and storage technologies. Because renewable sources are inconsistent, the best method to ensure supply continuity is to combine t...
详细信息
Ambient diffusion is a recently proposed framework for training diffusion models using corrupted data. Both Ambient Diffusion and alternative SURE-based approaches for learning diffusion models from corrupted data res...
详细信息
Ambient diffusion is a recently proposed framework for training diffusion models using corrupted data. Both Ambient Diffusion and alternative SURE-based approaches for learning diffusion models from corrupted data resort to approximations which deteriorate performance. We present the first framework for training diffusion models that provably sample from the uncorrupted distribution given only noisy training data, solving an open problem in Ambient diffusion. Our key technical contribution is a method that uses a double application of Tweedie's formula and a consistency loss function that allows us to extend sampling at noise levels below the observed data noise. We also provide further evidence that diffusion models memorize from their training sets by identifying extremely corrupted images that are almost perfectly reconstructed, raising copyright and privacy concerns. Our method for training using corrupted samples can be used to mitigate this problem. We demonstrate this by fine-tuning Stable Diffusion XL to generate samples from a distribution using only noisy samples. Our framework reduces the amount of memorization of the fine-tuning dataset, while maintaining competitive performance. Copyright 2024 by the author(s)
We study the risk-aware reinforcement learning (RL) problem in the episodic finite-horizon Markov decision process with unknown transition and reward functions. In contrast to the risk-neutral RL problem, we consider ...
详细信息
暂无评论