initialization

Tag

Cards List
#initialization

@andrew_n_carr: Turns out you can initialize an MLP with knowledge inside of it, no training required. Hazy research just showed that i…

X AI KOLs Timeline · 2026-07-22 Cached

Hazy Research showed that an MLP can be initialized with embedded knowledge without training, and a transformer can then query and use that knowledge, hinting at continual learning capabilities.

0 favorites 0 likes
#initialization

Complexity-Guided Component-wise Initialization for Language Model Pretraining

arXiv cs.CL · 2026-07-13 Cached

This paper analyzes spectral patterns in pretrained GPT-2-style language models and tests whether these patterns can be used for initialization, finding that coarse spectral matching does not improve pretraining performance over standard methods.

0 favorites 0 likes
#initialization

S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs -- From Dataset Geometry to Network Weights

arXiv cs.LG · 2026-06-30 Cached

S-GAI is a spectral geometry-aware initialization framework for one-hidden-layer sigmoidal MLPs that uses class-wise spectral geometry from image data to initialize weights, outperforming random initialization in terms of starting hidden state quality and achieving comparable final accuracy on benchmarks like MNIST and CIFAR-10.

0 favorites 0 likes
#initialization

Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation

Hugging Face Daily Papers · 2026-06-15 Cached

Taylor-Calibrate proposes a principled initialization method for hybrid linear attention models that significantly improves the efficiency of distilling pretrained Transformers into Gated DeltaNet students, achieving up to 88x improvement and reducing training tokens by 4.9x-9.2x.

0 favorites 0 likes
#initialization

There Is Life Before and After Main in Rust

Lobsters Hottest · 2026-06-11 Cached

A deep dive into what happens before the main function in Rust binaries, exploring runtime initialization, entry points, and novel techniques for mutable data initialization.

0 favorites 0 likes
#initialization

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias

arXiv cs.LG · 2026-05-29 Cached

This paper introduces the concept of 'initialization memory' to study how much of the random initialization bias survives training in deep networks, showing that low-learning-rate SGD preserves initialization while Adam-family optimizers erase it, and linking this to forgetting dynamics.

0 favorites 0 likes
← Back to home

Submit Feedback