Summary of Masks, Signs, and Learning Rate Rewinding, by Advait Gadhikar and Rebekka Burkholz
Masks, Signs, And Learning Rate Rewindingby Advait Gadhikar, Rebekka BurkholzFirst submitted to arxiv on: 29…
Masks, Signs, And Learning Rate Rewindingby Advait Gadhikar, Rebekka BurkholzFirst submitted to arxiv on: 29…
Batch size invariant Adamby Xi Wang, Laurence AitchisonFirst submitted to arxiv on: 29 Feb 2024CategoriesMain:…
On the Convergence of Differentially-Private Fine-tuning: To Linearly Probe or to Fully Fine-tune?by Shuqi Ke,…
Data Interpreter: An LLM Agent For Data Scienceby Sirui Hong, Yizhang Lin, Bang Liu, Bangbang…
Implicit Optimization Bias of Next-Token Prediction in Linear Modelsby Christos ThrampoulidisFirst submitted to arxiv on:…
Automated Machine Learning for Multi-Label Classificationby Marcel WeverFirst submitted to arxiv on: 28 Feb 2024CategoriesMain:…
Multi-objective Differentiable Neural Architecture Searchby Rhea Sanjay Sukthanker, Arber Zela, Benedikt Staffler, Samuel Dooley, Josif…
Escaping Local Optima in Global Placementby Ke Xue, Xi Lin, Yunqi Shi, Shixiong Kai, Siyuan…
Probabilistic Bayesian optimal experimental design using conditional normalizing flowsby Rafael Orozco, Felix J. Herrmann, Peng…
Large Language Models As Evolution Strategiesby Robert Tjarko Lange, Yingtao Tian, Yujin TangFirst submitted to…