arXiv:2606. 10068v1 Announce Type: cross Abstract: Hyperparameter Optimization (HPO) is essential for building high-performing ML/DL models, yet conventional optimizers often struggle in high-dimensional spaces where evaluations are costly and progress is diluted across many low-impact variables.
By Ruinan Wang, Ian Nabney, Mohammad Golbabaee
arXiv:2211. 14411v5 Announce Type: replace-cross Abstract: Hyperparameter optimization (HPO) is crucial for strong performance of deep learning algorithms and real-world applications often impose some constraints, such as on memory usage or latency, on top of the performance requirement.
By Shuhei Watanabe, Frank Hutter
arXiv:2606. 09601v1 Announce Type: new Abstract: Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimental factors.
By Berker Demirel, Valentino Maiorca, Marco Fumero, Theofanis Karaletsos, Francesco Locatello
Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional training.
arXiv:2607. 09739v1 Announce Type: new Abstract: We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the full benchmark suite.
By Jihan Yao, Gantavya Bhatt, Arnav Das, Peter Jin, Ke Bao, Qiaolin Yu, Khushi Bhardwaj, Chang Su, Jialei Wang, Yikai Zhu, Sugam Devare, Damon Mosk-Aoyama, Zhen Dong, Venkat Krishna Srinivasan, Yineng Zhang, Oleksii Kuchaiev, Jiantao Jiao, Banghua Zhu, Jeff Bilmes
arXiv:2606. 01544v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs.
By Cheonjun Park