Tagged “representation-learning”

3 posts.

All Model Architecture19 Training & Alignment22 Inference & Serving20 Agents & Orchestration11 Reasoning & Evaluation27 Safety, Security & Governance7 Platforms & Practice22

Platforms & Practice 25 min

Learning Without Labels: The Collapse Problem at the Heart of Self-Supervised Learning

Every joint-embedding method has the same trivial solution available to it: map every input to the same vector. The history of self-supervised learning is the history of preventing that, and the methods that look most different f…

self-supervised-learning contrastive-learning representation-learning embeddings ∑ ◫

Platforms & Practice 26 min

One Number, Two Knobs: The ELBO Is a Rate-Distortion Tradeoff

Two variational autoencoders can report the same ELBO to three decimal places while one has a latent code carrying five bits of information about the input and the other has a latent carrying exactly zero. The objective cannot se…

vae elbo rate-distortion representation-learning ∑ ◫

Reasoning & Evaluation 24 min

The Curse of Dimensionality: Why Distances Stop Meaning Anything, and Why Learning Works Anyway

Scatter 1,000 random points in a 1,000-dimensional cube and the farthest one from a query is only about 12% farther away than the nearest. By that arithmetic nearest-neighbour search should be meaningless, and yet every vector da…

supervised-classical learning-theory embeddings vector-search ∑ ◫