'Generalization on the Unseen, Logic Reasoning and Degree Curriculum', by Emmanuel Abbe, Samy Bengio, Aryo Lotfi, Kevin Rizk.
http://jmlr.org/papers/v25/24-0220.html
#sparse #learns #generalization
Recent searches
Search options
#learns
0 posts0 participants0 posts today
'Value-Distributional Model-Based Reinforcement Learning', by Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska, Felix Berkenkamp, Jan Peters.
http://jmlr.org/papers/v25/23-0913.html
#reinforcement #quantile #learns
'Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics', by Noga Mudrik, Yenho Chen, Eva Yezerets, Christopher J. Rozell, Adam S. Charles.
http://jmlr.org/papers/v25/23-0777.html
#dynamical #dynamics #learns
Representations and Computations in Transformers that Support Generalization on Structured Tasks
Yuxuan Li, James McClelland
Action editor: Stefan Lee.
When Less is More: Simplifying Inputs Aids Neural Network Understanding
FairGrad: Fairness Aware Gradient Descent
Gaurav Maheshwari, Michaël Perrot
Action editor: Novi Quadrianto.
SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration
Simplifying and Understanding State Space Models with Diagonal Linear RNNs
Two-Level Actor-Critic Using Multiple Teachers
FairGrad: Fairness Aware Gradient Descent
Reinforcement Teaching
Calarina Muslimani, Alex Lewandowski, Dale Schuurmans, Matthew E. Taylor, Jun Luo
Action editor: Marcello Restelli.
DCP: Learning Accelerator Dataflow for Neural Network via Propagation
GraphPNAS: Learning Probabilistic Graph Generators for Neural Architecture Search
Lightweight Learner for Shared Knowledge Lifelong Learning
Yunhao Ge, Yuecheng Li, Di Wu et al.
Action editor: Edward Grefenstette.
Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?
Tian Yun, Usha Bhalla, Ellie Pavlick, Chen Sun
Action editor: Zhe Gan.
FL Games: A federated learning framework for distribution shifts
Lightweight Learner for Shared Knowledge Lifelong Learning
L-SVRG and L-Katyusha with Adaptive Sampling
Boxin Zhao, Boxiang Lyu, mladen kolar
SLM: End-to-end Feature Selection via Sparse Learnable Masks
