conftrace_

Haiquan Lu

3 papers · 2024–2024 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

NeurIPS (2) ECCV (1)

Top co-authors

Yaoqing Yang (2) Michael W. Mahoney (2) Yefan Zhou (2) Kurt Keutzer (1) Le Zhang (1) Huanrui Yang (1) Qunli Li (1) Shiwei Liu (1) Xialei Liu (1) Xiaotian Liu (1)

Research topics

Machine Learning (2) Application Areas (2) Artificial Intelligence (1) Deep Learning (1) Natural Language Processing (1) Core AI (1) Core Methods (1) Optimization & Theory · Deep Learning (1) Optimization & Theory · Machine Learning (1) Resources & Methods (1)

Keywords

model compression (1) neural network pruning (1) out-of-distribution generalization (1) model pruning (1) weight matrix (1) layer-wise pruning (1) spectral density (1) robust generalization (1) deep ensemble (1) large language model (1) heavy-tailed self-regularization (1) empirical spectral density (1)

Papers

AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models NeurIPS 2024 Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation ECCV 2024 Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance NeurIPS 2024