📑

AI Paper Research

AI 논문 조사 및 정리

Foundations
최적화·학습이론Optimization & Learning Theory
The Road Less Scheduled
Symbolic Discovery of Optimization Algor...Sophia: A Scalable Stochastic Second-ord...
Tensor Programs V: Tuning Large Neural N...
Sharpness-Aware Minimization for Efficie...
The Lottery Ticket Hypothesis: Finding S...Large Batch Optimization for Deep Learni...
Decoupled Weight Decay RegularizationLarge Batch Training of Convolutional Ne...
Training Deep Nets with Sublinear Memory...
홈/최적화·학습이론/2022

최적화·학습이론 — 2022

1편의 논문

arXiv500+

Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer

텐서 프로그램 V: 제로샷 하이퍼파라미터 전이를 통한 대규모 신경망 튜닝

Greg Yang, Edward J. Hu, Igor Babuschkin et al. (2022)

← 최적화·학습이론 전체