ACCELERATING TRAINING OF TRANSFORMER-BASED LANGUAGE MODELS WITH PROGRESSIVE LAYER DROPPING

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 17 of 27
1. Verfasser: Zhang, Minjia (VerfasserIn)
Weitere Verfasser: He, Yuxiong (VerfasserIn)
Pages:34
Format: UnknownFormat
Sprache:eng
Veröffentlicht: 2021
Schlagworte:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Titel Jahr Verfasser
LATENT BANDITS REVISITED 2021 Hong, Joey
LINEAR TIME SINKHORN DIVERGENCES USING POSITIVE FEATURES 2021 Scetbon, Meyer
ADVERSARIAL COUNTERFACTUAL LEARNING AND EVALUATION FOR RECOMMENDER SYSTEM 2021 Xu, Da
EFFICIENT LEARNING OF DISCRETE GRAPHICAL MODELS 2021 Vuffray, Marc
SMOOTHED GEOMETRY FOR ROBUST ATTRIBUTION 2021 Wang, Zifan
O(N) CONNECTIONS ARE EXPRESSIVE ENOUGH: UNIVERSAL APPROXIMABILITY OF SPARSE TRANSFORMERS 2021 Yun, Chulhee
TRANSFERABLE GRAPH OPTIMIZERS FOR ML COMPILERS 2021 Zhou, Yanqi
RANET: REGION ATTENTION NETWORK FOR SEMANTIC SEGMENTATION 2021 Shen, Dingguo
SMOOTHLY BOUNDING USER CONTRIBUTIONS IN DIFFERENTIAL PRIVACY 2021 Epasto, Alessandro
LEARNING DEEP ATTRIBUTION PRIORS BASED ON PRIOR KNOWLEDGE 2021 Weinberger, Ethan
GROUP KNOWLEDGE TRANSFER: FEDERATED LEARNING OF LARGE CNNS AT THE EDGE 2021 He, Chaoyang
NEURAL FFTS FOR UNIVERSAL TEXTURE IMAGE SYNTHESIS 2021 Mardani, Morteza
NANOFLOW: SCALABLE NORMALIZING FLOWS WITH SUBLINEAR PARAMETER COMPLEXITY 2021 Lee, Sang-Gil
MOPO: MODEL-BASED OFFLINE POLICY OPTIMIZATION 2021 Yu, Tianhe
3D SHAPE RECONSTRUCTION FROM VISION AND TOUCH 2021 Smith, Edward
A GENERALIZED NEURAL TANGENT KERNEL ANALYSIS FOR TWO-LAYER NEURAL NETWORKS 2021 Chen, Zixiang
INTRA ORDER-PRESERVING FUNCTIONS FOR CALIBRATION OF MULTI-CLASS NEURAL NETWORKS 2021 Rahimi, Amir
PROMOTING STOCHASTICITY FOR EXPRESSIVE POLICIES VIA A SIMPLE AND EFFICIENT REGULARIZATION METHOD 2021 Zhou, Oi
SCALECOM: SCALABLE SPARSIFIED GRADIENT COMPRESSION FOR COMMUNICATION-EFFICIENT DISTRIBUTED TRAINING 2021 Chen, Chia-Yu
EVOLVING NORMALIZATION-ACTIVATION LAYERS 2021 Liu, Hanxiao
Alle Artikel auflisten