Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
gradient bias
Description:
A systematic deviation between a gradient used in an optimization or learning process and the corresponding unbiased gradient of the objective.
Related topics:
Reinforcement Learning in Robotics (16%),
Privacy-Preserving Technologies in Data (9%),
Stochastic Gradient Optimization Techniques (9%)
OpenAlex ID:
keywords/gradient-bias
Justifying and Generalizing Contrastive Divergence
2008
·
Yoshua Bengio
, Olivier Delalleau
·
Neural Computation
·
242
Understanding and correcting pathologies in the training of learned optimizers
2018
·
Metz, Luke
, Maheswaranathan, Niru
, et al.
·
arXiv (Cornell University)
·
149
PDF
Unbiasing Truncated Backpropagation Through Time
2017
·
Tallec, Corentin
, Ollivier, Yann
·
HAL
·
111
PDF
Parallel tempering is efficient for learning restricted Boltzmann machines
2010
·
KyungHyun Cho
, Tapani Raiko
, et al.
·
International Joint Conference on Neural Networks (IJCNN)
·
103
Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating
2019
·
Yao, Xin
, Huang, Tianchi
, et al.
·
arXiv (Cornell University)
·
93
PDF
Why Do We Need Large Batchsizes in Contrastive Learning? A Gradient-Bias Perspective
2022
·
Changyou Chen
, Jianyi Zhang
, et al.
·
neural information processing systems
·
69
D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning
2022
·
Aurelien Bellet
, Anne-Marie Kermarrec
, et al.
·
IEEE Symposium on Reliable Distributed Systems (SRDS)
·
63
PDF
Projective Sampling for Differentiable Rendering of Geometry
2023
·
Ziyi Zhang
, Nicolas Roussel
, et al.
·
ACM Transactions on Graphics
·
55
IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression
2020
·
Berg, Rianne van den
, Gritsenko, Alexey A.
, et al.
·
arXiv (Cornell University)
·
51
PDF
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
2026
·
Wu, Yecheng
, Han, Song
, et al.
·
arXiv (Cornell University)
·
45
PDF
Adaptively Truncating Backpropagation Through Time to Control Gradient Bias
2019
·
Aicher, Christopher
, Foti, Nicholas J.
, et al.
·
arXiv (Cornell University)
·
43
PDF
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach
2022
·
Fernando, Heshan
, Shen, Han
, et al.
·
arXiv (Cornell University)
·
31
PDF
Gradient-Aware for Class-Imbalanced Semi-supervised Medical Image Segmentation
2024
·
Wenbo Qi
, Jiafei Wu
, et al.
·
Lecture notes in computer science
·
30
Gradient Informed Proximal Policy Optimization
2023
·
Sanghyun Son
, Laura Zheng
, et al.
·
neural information processing systems
·
29
PDF
Reinforcement Recommendation with User Multi-aspect Preference
2021
·
Xu Chen
, Yali Du
, et al.
·
International World Wide Web Conference (WWW)
·
26
A Comedy of Estimators: On KL Regularization in RL Training of LLMs
2025
·
Shah, Vedant
, Obando-Ceron, Johan
, et al.
·
arXiv (Cornell University)
·
25
PDF
Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descent
2022
·
Ian Gemp
, Rahul Savani
, et al.
·
Adaptive Agents and Multi-Agents Systems
·
25
PDF
Portfolio optimization using deep learning with risk aversion utility function
2025
·
Kenji Kubo
, Kei Nakagawa
·
Finance research letters
·
21
Train Hard, Fight Easy: Robust Meta Reinforcement Learning
2023
·
Ido Greenberg
, Shie Mannor
, et al.
·
neural information processing systems
·
20
PDF
On the Convergence of Consensus Algorithms with Markovian noise and Gradient Bias
2020
·
Hoi-To Wai
·
IEEE Conference on Decision and Control (CDC)
·
17
PDF
Learning Item Representations Directly from Multimodal Features for Effective Recommendation
2025
·
Zhou, Xin
, Zhang, Xiaoxiong
, et al.
·
arXiv (Cornell University)
·
15
PDF
Gradient Estimation for Unseen Domain Risk Minimization with Pre-Trained Models
2023
·
Byounggyu Lew
, Donghyun Son
, et al.
·
IEEE International Conference on Computer Vision Workshops
·
15
PDF
IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression
2021
·
Rianne van den Berg
, Alexey A. Gritsenko
, et al.
·
15
SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching
2021
·
Sun, Mingfei
, Mahajan, Anuj
, et al.
·
arXiv (Cornell University)
·
14
PDF
D-Cliques: Compensating NonIIDness in Decentralized Federated Learning with Topology.
2021
·
Aurélien Bellet
, Anne-Marie Kermarrec
, et al.
·
arXiv (Cornell University)
·
13
Show more works
View as search
Works count:
108
Citation count:
1,571
Year
Topic
Type