Unverified50% confidenceFactExact time
The reparameterization trick, proposed by Kingma and Welling in 2013, enables gradients to backpropagate through the sampling step by transforming the stochastic sampling operation into a deterministic computation plus noise.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified重参数化技巧将采样表示为 z = μ + σ × ε（ε从标准正态分布采样），使随机性外置于ε，从而让μ和σ的梯度可正常反向传播实现端到端训练66% similarUnverifiedThe choice of sampler has a pivotal impact on the final quality of diffusion model inference; common samplers include Euler, DPM++, DDIM, and the SDE series, which are essentially different numerical solving strategies for stochastic or ordinary differential equations.65% similarUnverifiedConsistency models attempt to compress the multi-step denoising process of diffusion models into 1–4 steps, theoretically capable of improving inference speed by 10–50 times.65% similarUnverifiedDifferent LLM models vary in their accuracy of understanding instructions; it is recommended to iteratively optimize prompts multiple times to achieve the best results.65% similarVerifiedBayesian optimization constructs a probabilistic surrogate model of the objective function (typically a Gaussian process) and uses an acquisition function (such as Expected Improvement or Upper Confidence Bound) to determine the next sampling point.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/895921API
curl https://kongchang.com/api/v1/knowledge/claims/895921MCP
get_claim(id=895921)