NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#markov-chains

0 stories this week · 3 this month · 3 in 6 months · mostly AI

Stories per day · 30 days

Relatedtheory2 algorithmic-threshold1 black-box1 cs-cr1 differential-privacy1 fingerprinting1 langevin-dynamics1 llm-agents1 model-attribution1 sample-complexity1 tensor-pca1 user-level-privacy1

3 stories, newest first · one card per story

arXiv cs.AI / cs.LG / cs.CL14d ago

Annealed Langevin dynamics reach the tensor PCA algorithmic threshold

Part II says spherical Langevin dynamics with annealing and averaging strongly recover from a random start.

tensor-pca langevin-dynamics

arXiv cs.CR19d ago

AgentTrace fingerprints black-box LLM agents from execution traces

Markov models of repair sequences reach 96.0% attribution accuracy and separate Llama-3 8B from 70B under spoofing.

llm-agents model-attribution

1

arXiv cs.CR28d ago

Differentially Private Learning of Markov Chains: Near-Optimal Sample Complexity for Item and User Level Privacy

Researchers give near-optimal private bounds for learning Markov chain transition matrices.

differential-privacy markov-chains

3