9 papers · 1 filter
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
Peng Wang, Xiao Li, Can Yaras +4
Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks…
Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws
Zhiwei Xu, Shihao Wu, Hanseul Cho +2
Classical scaling laws for language model pretraining balance model size against training dataset size under a fixed compute budget, assuming abundant data and a single pass over t…
Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling
Junyi Yao, Parham Eftekhar, Gene Cheung +3
Samples of brain signals collected by EEG sensors have inherent anti-correlations that are well modeled by negative edges in a finite graph. To differentiate epilepsy patients from…
RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm
Yongyi Yang, Jianyang Gao, Wei Hu
Post-training Quantization (PTQ) has become a widely used technique for improving inference efficiency of large language models (LLMs). However, existing PTQ methods generally suff…
Swing-by Dynamics in Concept Learning and Compositional Generalization
Yongyi Yang, Core Francisco Park, Ekdeep Singh Lubana +3
Prior work has shown that text-conditioned diffusion models can learn to identify and manipulate primitive concepts underlying a compositional data-generating process, enabling gen…
What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
Pulkit Gopalani, Wei Hu
Training Transformers on algorithmic tasks frequently demonstrates an intriguing abrupt learning phenomenon: an extended performance plateau followed by a sudden, sharp improvement…