Segueix
Yi Zhang
Yi Zhang
Senior Researcher at Microsoft Research Redmond
Correu electrònic verificat a microsoft.com - Pàgina d'inici
Títol
Citada per
Citada per
Any
Sparks of artificial general intelligence: Early experiments with gpt-4
S Bubeck, V Chadrasekaran, R Eldan, J Gehrke, E Horvitz, E Kamar, ...
ArXiv, 2023
37652023
Generalization and Equilibrium in Generative Adversarial Nets (GANs)
S Arora, R Ge, Y Liang, T Ma, Y Zhang
arXiv preprint arXiv:1703.00573, 2017
8472017
Phi-3 technical report: A highly capable language model locally on your phone
M Abdin, J Aneja, H Awadalla, A Awadallah, AA Awan, N Bach, A Bahree, ...
arXiv preprint arXiv:2404.14219, 2024
8322024
Stronger generalization bounds for deep nets via a compression approach
S Arora, R Ge, B Neyshabur, Y Zhang
International conference on machine learning, 254-263, 2018
7182018
Convolutional neural networks with low-rank regularization
C Tai, T Xiao, Y Zhang, X Wang
arXiv preprint arXiv:1511.06067, 2015
5672015
Textbooks are all you need
S Gunasekar, Y Zhang, J Aneja, CCT Mendes, A Del Giorno, S Gopi, ...
arXiv preprint arXiv:2306.11644, 2023
5612023
Deep visual analogy-making
SE Reed, Y Zhang, Y Zhang, H Lee
Advances in neural information processing systems 28, 2015
3792015
Phi-2: The surprising power of small language models
M Javaheripi, S Bubeck, M Abdin, J Aneja, S Bubeck, CCT Mendes, ...
Microsoft Research Blog 1 (3), 3, 2023
2092023
Do GANs actually learn the distribution? An empirical study
S Arora, Y Zhang
arXiv:1706.08224, 2017
2042017
Do GANs learn the distribution? some theory and empirics
S Arora, A Risteski, Y Zhang
International conference on learning representations, 2018
1862018
Spectral filtering for general linear dynamical systems
E Hazan, H Lee, K Singh, C Zhang, Y Zhang
Advances in Neural Information Processing Systems 31, 2018
1142018
What makes convolutional models great on long sequence modeling?
Y Li, T Cai, Y Zhang, D Chen, D Dey
arXiv preprint arXiv:2210.09298, 2022
1062022
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
R Kuditipudi, X Wang, H Lee, Y Zhang, Z Li, W Hu, S Arora, R Ge
arXiv:1906.06247, 2019
982019
Towards Understanding the Invertibility of Convolutional Neural Networks
CA Gilbert, Y Zhang, K Lee, Y Zhang, H Lee
arXiv preprint arXiv:1705.08664, 2017
812017
Unveiling transformers with lego: a synthetic reasoning task
Y Zhang, A Backurs, S Bubeck, R Eldan, S Gunasekar, T Wagner
arXiv preprint arXiv:2206.04301, 2022
722022
Efficient full-matrix adaptive regularization
N Agarwal, B Bullins, X Chen, E Hazan, K Singh, C Zhang, Y Zhang
International Conference on Machine Learning, 102-110, 2019
682019
Why are convolutional nets more sample-efficient than fully-connected nets?
Z Li, Y Zhang, S Arora
arXiv preprint arXiv:2010.08515, 2020
602020
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
Y Zhang, O Plevrakis, SS Du, X Li, Z Song, S Arora
arXiv:2002.06668, 2020
542020
Learning threshold neurons via the "edge of stability"
K Ahn, S Bubeck, S Chewi, YT Lee, F Suarez, Y Zhang
arxiv.org/2212.07469, 2022
452022
Tinygsm: achieving> 80% on gsm8k with small language models
B Liu, S Bubeck, R Eldan, J Kulkarni, Y Li, A Nguyen, R Ward, Y Zhang
arXiv preprint arXiv:2312.09241, 2023
442023
En aquests moments el sistema no pot dur a terme l'operació. Torneu-ho a provar més tard.
Articles 1–20