Beyond Gradient Averaging in Parallel Optimization (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Beyond Gradient Averaging in Parallel Optimization

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: No More Adam: Learning Rate Scaling at Initialization Is All You Need

No More Adam: Learning Rate Scaling at Initialization Is All You Need (arxiv.org)

84 points by jinqueeny 1 year ago | 23 comments

Screenshot of arxiv.org: Offline Reinforcement Learning for LLM Multi-Step Reasoning

Offline Reinforcement Learning for LLM Multi-Step Reasoning (arxiv.org)

86 points by belter 1 year ago | 7 comments

Screenshot of arxiv.org: Classical sorting algorithms as a model of morphogenesis (2023)

Classical sorting algorithms as a model of morphogenesis (2023)(arxiv.org)

157 points by filoeleven 1 year ago | 70 comments

Screenshot of arxiv.org: Invariants: Computation and Applications

Invariants: Computation and Applications (arxiv.org)

38 points by crete 1 year ago | 1 comments

Screenshot of arxiv.org: Tokenisation Is NP-Complete

Tokenisation Is NP-Complete (arxiv.org)

100 points by belter 1 year ago | 20 comments

Screenshot of arxiv.org: Adversarial policies beat superhuman Go AIs (2023)

Adversarial policies beat superhuman Go AIs (2023)(arxiv.org)

299 points by amichail 1 year ago | 129 comments