Unverified50% confidenceFactExact time
The DP-μP framework derives a signal-to-noise ratio (SNR) condition that characterizes the relative strength of signal and noise at each layer under the DP constraint, and based on this determines how learning rates should scale across layers.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDP-μP proposes a spectral scaling formula that combines the SNR condition with matrix spectral properties to give concrete scaling rules for different optimizers.75% similarUnverifiedD²NN arranges multiple layers of trainable diffractive planes, with the transmission or reflection coefficient of each micro-element serving as a learnable parameter; after optimization, these are fixed as a physical structure, and the diffraction and interference that occur as light passes through equivalently perform forward inference.67% similarVerifiedThe denoising process of diffusion models is based on the DDPM principle, which involves progressively adding Gaussian noise to data during training and then training a neural network to learn the reverse denoising process.65% similarUnverifiedDiffusion models achieve generation and denoising by training a network to approximate the score function ∇_x log p_σ(x) at each noise level.65% similarUnverifiedFD-VAD is a method that models semantic endpoint detection as a causal audio-language reasoning task, directly mapping from a limited causal audio window to a binary continue/stop decision without ASR involvement.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1068348API
curl https://kongchang.com/api/v1/knowledge/claims/1068348MCP
get_claim(id=1068348)