default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDZiyin Liu
Person information
Other persons with a similar name
SPARQL queries 
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[c17]Ziyin Liu:
Symmetry Induces Structure and Constraint of Learning. ICML 2024- [c16]Yi Yuan
, Guiyun Zhou, Zhonghua Su, Ziyin Liu, Weiwei Sun, Xiangchao Meng, Jie Wen, Zhiqiang Wu:
A Lightweight and Enhanced Semantic Segmentation Network for Mapping of Retrogressive Thaw Slumps from Sentinel-2 Images. IGARSS 2024: 130-133 - [i30]Yizhou Xu, Ziyin Liu:
When Does Feature Learning Happen? Perspective from an Analytically Solvable Model. CoRR abs/2401.07085 (2024) - [i29]Ziyin Liu, Mingze Wang, Lei Wu:
The Implicit Bias of Gradient Noise: A Symmetry Perspective. CoRR abs/2402.07193 (2024) - [i28]Ziyin Liu, Yizhou Xu, Isaac Chuang:
Remove Symmetries to Control Model Expressivity. CoRR abs/2408.15495 (2024) - [i27]Ziyin Liu, Isaac Chuang, Tomer Galanti, Tomaso A. Poggio:
Formation of Representations in Neural Networks. CoRR abs/2410.03006 (2024) - 2023
- [c15]Ziyin Liu, Ekdeep Singh Lubana, Masahito Ueda, Hidenori Tanaka:
What shapes the loss landscape of self supervised learning? ICLR 2023 - [c14]James B. Simon, Maksis Knutins, Ziyin Liu, Daniel Geisz, Abraham J. Fetterman, Joshua Albrecht:
On the Stepwise Nature of Self-Supervised Learning. ICML 2023: 31852-31876 - [c13]Ziyin Liu, Zihao Wang:
spred: Solving L1 Penalty with SGD. ICML 2023: 43407-43422 - [i26]Ziyin Liu, Botao Li, Tomer Galanti, Masahito Ueda:
The Probabilistic Stability of Stochastic Gradient Descent. CoRR abs/2303.13093 (2023) - [i25]James B. Simon, Maksis Knutins, Ziyin Liu, Daniel Geisz, Abraham J. Fetterman, Joshua Albrecht:
On the stepwise nature of self-supervised learning. CoRR abs/2303.15438 (2023) - [i24]Ziyin Liu, Hongchao Li, Masahito Ueda:
Law of Balance and Stationary Distribution of Stochastic Gradient Descent. CoRR abs/2308.06671 (2023) - [i23]Ziyin Liu:
Symmetry Leads to Structured Constraint of Learning. CoRR abs/2309.16932 (2023) - 2022
- [c12]Ziyin Liu, Kentaro Minami, Kentaro Imajo:
Theoretically Motivated Data Augmentation and Regularization for Portfolio Construction. ICAIF 2022: 273-281 - [c11]Ziyin Liu, Kangqiao Liu, Takashi Mori, Masahito Ueda:
Strength of Minibatch Noise in SGD. ICLR 2022 - [c10]Ziyin Liu, Botao Li, James B. Simon, Masahito Ueda:
SGD Can Converge to Local Maxima. ICLR 2022 - [c9]Takashi Mori, Ziyin Liu, Kangqiao Liu, Masahito Ueda:
Power-Law Escape Rate of SGD. ICML 2022: 15959-15975 - [c8]Zihao Wang, Ziyin Liu:
Posterior Collapse of a Linear Latent Variable Model. NeurIPS 2022 - [c7]Ziyin Liu, Botao Li, Xiangming Meng:
Exact Solutions of a Deep Linear Network. NeurIPS 2022 - [i22]Ziyin Liu, Hanlin Zhang, Xiangming Meng, Yuting Lu, Eric P. Xing, Masahito Ueda:
Stochastic Neural Networks with Infinite Width are Deterministic. CoRR abs/2201.12724 (2022) - [i21]Ziyin Liu, Botao Li, Xiangming Meng:
Exact Solutions of a Deep Linear Network. CoRR abs/2202.04777 (2022) - [i20]Zihao Wang, Ziyin Liu:
Posterior Collapse of a Linear Latent Variable Model. CoRR abs/2205.04009 (2022) - [i19]Ziyin Liu, Masahito Ueda:
Exact Phase Transitions in Deep Learning. CoRR abs/2205.12510 (2022) - [i18]Ziyin Liu, Ekdeep Singh Lubana, Masahito Ueda, Hidenori Tanaka:
What shapes the loss landscape of self-supervised learning? CoRR abs/2210.00638 (2022) - [i17]Ziyin Liu, Zihao Wang:
Sparsity by Redundancy: Solving L1 with a Simple Reparametrization. CoRR abs/2210.01212 (2022) - 2021
- [c6]Kangqiao Liu, Ziyin Liu, Masahito Ueda:
Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent. ICML 2021: 7045-7056 - [c5]Paul Pu Liang, Peter Wu, Ziyin Liu, Louis-Philippe Morency, Ruslan Salakhutdinov:
Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment. ACM Multimedia 2021: 2680-2689 - [c4]Zhiyi Zhang, Ziyin Liu:
On the distributional properties of adaptive gradients. UAI 2021: 419-429 - [i16]Ziyin Liu, Kangqiao Liu, Takashi Mori, Masahito Ueda:
On Minibatch Noise: Discrete-Time SGD, Overparametrization, and Bayes. CoRR abs/2102.05375 (2021) - [i15]Zhiyi Zhang, Ziyin Liu:
On the Distributional Properties of Adaptive Gradients. CoRR abs/2105.07222 (2021) - [i14]Takashi Mori, Ziyin Liu, Kangqiao Liu, Masahito Ueda:
Logarithmic landscape and power-law escape rate of SGD. CoRR abs/2105.09557 (2021) - [i13]Ziyin Liu, Kentaro Minami, Kentaro Imajo:
What Data Augmentation Do We Need for Deep-Learning-Based Finance? CoRR abs/2106.04114 (2021) - [i12]Ziyin Liu, Botao Li, Masahito Ueda:
SGD May Never Escape Saddle Points. CoRR abs/2107.11774 (2021) - 2020
- [c3]Ziyin Liu, Tilman Hartwig, Masahito Ueda:
Neural Networks Fail to Learn Periodic Functions and How to Fix It. NeurIPS 2020 - [i11]Paul Pu Liang, Terrance Liu, Ziyin Liu, Ruslan Salakhutdinov, Louis-Philippe Morency:
Think Locally, Act Globally: Federated Learning with Local and Global Representations. CoRR abs/2001.01523 (2020) - [i10]Ziyin Liu, Zhikang Wang, Masahito Ueda:
LaProp: a Better Way to Combine Momentum with Adaptive Gradient. CoRR abs/2002.04839 (2020) - [i9]Ziyin Liu, Blair Chen, Ru Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda:
Learning Not to Learn in the Presence of Noisy Labels. CoRR abs/2002.06541 (2020) - [i8]Ziyin Liu, Zihao Wang, Makoto Yamada, Masahito Ueda:
Volumization as a Natural Generalization of Weight Decay. CoRR abs/2003.11243 (2020) - [i7]Ziyin Liu, Tilman Hartwig, Masahito Ueda:
Neural Networks Fail to Learn Periodic Functions and How to Fix It. CoRR abs/2006.08195 (2020) - [i6]Blair Chen, Ziyin Liu, Zihao Wang, Paul Pu Liang:
An Investigation of how Label Smoothing Affects Generalization. CoRR abs/2010.12648 (2020) - [i5]Paul Pu Liang, Peter Wu, Ziyin Liu, Louis-Philippe Morency, Ruslan Salakhutdinov:
Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment. CoRR abs/2012.02813 (2020) - [i4]Kangqiao Liu, Ziyin Liu, Masahito Ueda:
Stochastic Gradient Descent with Large Learning Rate. CoRR abs/2012.03636 (2020)
2010 – 2019
- 2019
- [c2]Ziyin Liu, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda:
Deep Gamblers: Learning to Abstain with Portfolio Theory. NeurIPS 2019: 10622-10632 - [i3]Ziyin Liu, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda:
Deep Gamblers: Learning to Abstain with Portfolio Theory. CoRR abs/1907.00208 (2019) - 2018
- [c1]Paul Pu Liang, Ziyin Liu, Amir Zadeh, Louis-Philippe Morency:
Multimodal Language Analysis with Recurrent Multistage Fusion. EMNLP 2018: 150-161 - [i2]Paul Pu Liang, Ziyin Liu, Amir Zadeh, Louis-Philippe Morency:
Multimodal Language Analysis with Recurrent Multistage Fusion. CoRR abs/1808.03920 (2018) - [i1]Yixiu Zhao, Ziyin Liu:
BlockPuzzle - A Challenge in Physical Reasoning and Generalization for Robot Learning. CoRR abs/1812.00091 (2018)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-08 20:26 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
